paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

The Ensemble Schr{ö}dinger Bridge filter for Nonlinear Data Assimilation

Hui Sun

This work introduces a novel nonlinear optimal filtering method, termed the Ensemble Schr{ö}dinger Bridge nonlinear filter. The proposed filter combines the standard prediction step with a diffusion-generative-modeling-based analysis step, thereby completing one full filtering update. The resulting approach introduces no structural model error, and is derivative-free, training-free, and highly parallelizable. Numerical experiments demonstrate that the proposed algorithm performs effectively for highly nonlinear dynamics and nonlinear observation processes, including chaotic systems with dimension up to 40 and beyond. The results also show that the method outperforms classical approaches such as the ensemble Kalman filter and particle filter across a range of tests with varying degrees of nonlinearity. Future work will focus on extending the proposed method to practical meteorological applications and developing a rigorous convergence theory.

arXiv

Target-Aware Early Stage Ranking

Juhee Hong, Meng Liu, Shengzhi Wang, Jin Zhou, Xiaoheng Mao, Zhao Zhu, Ruochen Liu, Huihui Cheng, Leon Gao, Christopher Leung, Chandra Mouli Sekar, Yijia Liu, Boyang Yu, Tuan Trieu, Dawei Sun, Jeet Kanjani, Rui Li, Jing Qian, Xuan Cao, Minjie Fan, Mingze Gao

Early Stage Ranking (ESR) in large-scale recommendation systems is dominated by ''user--item decoupling'' Two Tower architectures, which scale efficiently but cannot capture fine-grained, target-aware user--item interactions directly. We propose Target-Aware Early Stage Ranking (TESR), which augments the Two Tower with a Mixture of Attention (MoA) module trained as a request-level sequence modeling over user history. MoA combines (i) Hard Matching Attention (HMA) to capture explicit categorical-ID level overlap signals between user history and candidate item, (ii) target-aware HSTU attention for implicit affinities conditioned on the candidate, and (iii) target dependent and independent cross-attention for symmetric user-item contextualization. On top of this, a Multi-Logit Parameterized Gating (MLPG) head amplifies these signals at scoring time. To keep latency within ESR budgets, we co-design the architecture with FP8 quantization, custom kernels, and a Torch Inductor compilation path. On a production deployment, TESR delivers consistent offline NE wins and online topline gains, and is, to our knowledge, the first deployment of full target-aware attention sequence modeling in an ESR stage at this scale.

arXiv

Design Criteria for SGD Preconditioners: Local Conditioning, Noise Floors, and Basin Stability

Mitchell Scott, Tianshi Xu, Ziyuan Tang, Alexandra Pichette-Emmons, Qiang Ye, Yousef Saad, Yuanzhe Xi

Stochastic Gradient Descent (SGD) often slows in the late stage of training due to anisotropic curvature and gradient noise. We analyze preconditioned SGD in the geometry induced by a symmetric positive definite matrix $\mathbf{M}$, deriving bounds in which both the convergence rate and the stochastic noise floor are governed by $\mathbf{M}$-dependent quantities: the rate through an effective condition number in the $\mathbf{M}$-metric, and the floor through the product of that condition number and the preconditioned noise level. For nonconvex objectives, we establish a preconditioner-dependent basin-stability guarantee: when smoothness and basin size are measured in the $\mathbf{M}$-norm, the probability that the iterates remain in a well-behaved local region admits an explicit lower bound. This perspective is particularly relevant in Scientific Machine Learning (SciML), where achieving small training loss under stochastic updates is closely tied to physical fidelity, numerical stability, and constraint satisfaction. The framework applies to both diagonal/adaptive and curvature-aware preconditioners and yields a simple design principle: choose $\mathbf{M}$ to improve local conditioning while attenuating noise. Experiments on a quadratic diagnostic and three SciML benchmarks validate the predicted rate-floor behavior.

arXiv

STREAM-VAE: Dual-Path Routing for Slow and Fast Dynamics in Vehicle Telemetry Anomaly Detection

Kadir-Kaan Özer, René Ebeling, Markus Enzweiler

Automotive telemetry data exhibits slow drifts and fast spikes, often within the same sequence, making reliable anomaly detection challenging. Standard reconstruction-based methods, including sequence variational autoencoders (VAEs), use a single latent process and therefore mix heterogeneous time scales, which can smooth out spikes or inflate variances and weaken anomaly separation. In this paper, we present STREAM-VAE, a variational autoencoder for anomaly detection in automotive telemetry time-series data. Our model uses a dual-path encoder to separate slow drift and fast spike signal dynamics, and a decoder that represents transient deviations separately from the normal operating pattern. STREAM-VAE is designed for deployment, producing stable anomaly scores across operating modes for both in-vehicle monitors and backend fleet analytics. Experiments on an automotive telemetry dataset and the public SMD benchmark show that explicitly separating drift and spike dynamics improves robustness compared to strong forecasting, attention, graph, and VAE baselines.

arXiv

Target-Aligned Fusion for Decision-Sequence Learning under Dynamics Shift

Guojian Wang, Quinson Hon, Xuyang Chen, Lin Zhao

External trajectories can improve offline decision-sequence learning, but dynamics shift may make some source subsequences inconsistent with the target environment. We study how to fuse such trajectories with limited target data for Decision Transformer learning under dynamics shift. We propose Target-Aligned Fusion (TAF), a principled framework that derives source-data fusion from a target-domain Bellman-risk criterion. Our analysis bounds this risk by two measurable data-alignment quantities: $Δ_m$, the state-structure mismatch of retained fragments, and $Δ_w$, the weighted transport cost from source to target transitions. This decomposition yields a gate--then--weight rule: source fragments are first filtered by target-side state-structure alignment, and retained transitions are then reweighted by local target feasibility. We instantiate this principle as TAF-DT, which uses maximum mean discrepancy (MMD) for fragment selection, optimal transport for feasibility-aware weighting, and the resulting fused law for advantage-token relabeling and Q-regularized Transformer training. Across gravity, kinematic, and morphology shifts on D4RL-style control tasks, TAF-DT achieves the strongest aggregate performance against strong offline RL and sequence-model baselines and produces more stable stitch-junction sequence semantics. Overall, these results indicate that aligning external trajectories to target-domain structure and feasibility is a practical way to exploit source data under dynamics shift.

arXiv

Enhancing Q-Value Updates in Deep Q-Learning via Successor-State Prediction

Lipeng Zu, Hansong Zhou, Xiaonan Zhang

Deep Q-Networks (DQNs) estimate future returns by learning from transitions sampled from a replay buffer. However, the target updates in DQN often rely on next states generated by actions from past, potentially suboptimal, policy. As a result, these states may not provide informative learning signals, causing high variance into the update process. This issue is exacerbated when the sampled transitions are poorly aligned with the agent's current policy. To address this limitation, we propose the Successor-state Aggregation Deep Q-Network (SADQ), which explicitly models environment dynamics using a stochastic transition model. SADQ integrates successor-state distributions into the Q-value estimation process, enabling more stable and policy-aligned value updates. Additionally, it explores a more efficient action selection strategy with the modeled transition structure. We provide theoretical guarantees that SADQ maintains unbiased value estimates while reducing training variance. Our extensive empirical results across standard RL benchmarks and real-world vector-based control tasks demonstrate that SADQ consistently outperforms DQN variants in both stability and learning efficiency.

arXiv

Bridging Prediction and Attribution: Identifying Forward and Backward Causal Influence Ranges Using Assimilative Causal Inference

Marios Andreou, Nan Chen

Causal inference identifies cause-and-effect relationships between variables. While traditional approaches rely on data to reveal causal links, a recently developed method, assimilative causal inference (ACI), integrates observations with dynamical models. It utilizes Bayesian data assimilation to trace causes back from observed effects by quantifying the reduction in uncertainty. ACI advances the detection of instantaneous causal relationships and the intermittent reversal of causal roles over time. Beyond identifying causal connections, an equally important challenge is determining the associated causal influence range (CIR), indicating when causal influences emerged and for how long they persist. In this paper, ACI is employed to develop mathematically rigorous formulations of both forward and backward CIRs at each time. The forward CIR quantifies the temporal impact of a cause, while the backward CIR traces the onset of triggers for an observed effect, thus characterizing causal predictability and attribution of outcomes at each transient phase, respectively. Objective and robust metrics for both CIRs are introduced, eliminating the need for empirical thresholds. Computationally efficient approximation algorithms to compute CIRs are developed, which facilitate the use of closed-form expressions for a broad class of nonlinear dynamical systems. Numerical simulations demonstrate how this forward and backward CIR framework provides new possibilities for probing complex dynamical systems. It advances the study of bifurcation-driven and noise-induced tipping points in Earth systems, investigates the impact from resolving the interfering variables when determining the influence ranges, and elucidates atmospheric blocking mechanisms in the equatorial region. These results have direct implications for science, policy, and decision-making.

arXiv

Heteroscedasticity of Denoising Score Matching with Generalised Smooth Noise

Juyan Zhang, Rhys Newbury, Xinyang Zhang, Tin Tran, Dana Kulic, Michael Burke

Score Matching (SM) is a powerful framework for estimating the log-density derivatives of a distribution without calculating its normalizing constants. This capability has made it a cornerstone across multiple domains, from classical sta- tistical estimation and energy-based models to modern diffusion-based generative models. In practice, these models rely almost exclusively on Denoising Score Matching (DSM) as a tractable proxy for score matching. This ubiquity naturally raises a fundamental question: Is DSM truly "score matching for free"? In this work, we demonstrate that DSM is not a perfect substitute. We prove that the denoising objective is inherently heteroscedastic, the variance of model parame- ters fluctuates unpredictably based on both noise levels and the underlying data geometry. This instability is baked into the mathematical structure of the DSM. To address this, we derive an ideal weighting function that equalizes this variance, yielding a homoscedastic generalization of DSM. Since the ideal weights are of- ten empirically inaccessible, we show that a practical approximation weighting function via Taylor expansion reduces gradient variance during training, at the cost of statistical optimality. Notably, this provides a theoretical justification for an existing heuristic weight used in Isotropic Gaussian Diffusion. We validate our theory across different perturbed distributions and for higher-order scores.

arXiv

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model

Yeong-Joon Ju, Seong-Whan Lee

Adapting generative Multimodal Large Language Models (MLLMs) into universal embedding models typically demands resource-intensive contrastive pre-training, while traditional hard negative mining methods suffer from severe false negative contamination. In this paper, we propose a highly data-efficient framework that bypasses extensive pre-training to build a robust multimodal representation space. We first introduce a hierarchical embedding prompt that provides strong latent conditioning. By explicitly anchoring task definitions at the system level, this prompting strategy effectively bridges the modality gap and unlocks powerful zero-shot embedding capabilities. Building upon this latent conditioning, we present Self-aware Hard Negative Sampling (SaHa). Unlike conventional candidate-space mining, SaHa shifts the mechanism to the query-space by mapping retrieved candidates back to their owner queries to rigorously filter out semantic false negatives. Furthermore, our method constructs mutually hard clusters, maximizing intra-task discrimination and batch efficiency without redundant forward passes. Extensive experiments demonstrate that our unified approach achieves highly competitive fine-tuning performance on the Massive Multimodal Embedding Benchmark using only a fraction of standard training data.

arXiv

IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning

Jaeheun Jung, Jaehyuk Lee, Yeajin Lee, Donghun Lee

Importance-based structured pruning overwhelmingly relies on filter magnitude. This proxy is fundamentally flawed: due to scale invariance, functionally identical filters can receive arbitrarily different importance scores under rescaling. We propose IPPRO (Importance-based Pruning with PROjective Offset), a scale-invariant pruning framework grounded in projective geometry. By embedding filters into real projective space ($\mathbb{RP}^N$), IPPRO resolves the singularity at the origin, placing all filters at an equal angular distance from the zero filter. We define PROscore, which captures functional importance by measuring a filter's angular displacement toward zero under a single gradient step (directional collapse). We further connect PROscore to exact $L_0$ relaxation, proving this one-shot criterion reliably predicts multi-step pruning dynamics. Extensive experiments across CNNs, Vision Transformers, and LLMs (e.g., ResNet, DeiT, LLaMA) demonstrate that IPPRO consistently outperforms existing methods, yielding particularly striking gains under high compression and no-fine-tuning regimes, IPPRO establishes a robust, architecture-agnostic paradigm for neural network compression.

arXiv

One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting

Jaeheun Jung, Bosung Jung, Suhyun Bae, Donghun Lee

Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores. We show that this is not enough. Across 14 representative unlearning methods on CIFAR-10 and SVHN, a single linear map fitted on a held-out calibration set, with no access to the forgotten data, reverses the unlearning in seconds and recovers forget-set accuracy to within a few percent of the original model. Recovered features even support pixel-level reconstruction through a generic decoder. We call this diagnostic Feature Mapping Recovery (FM-recovery). The pattern it exposes is uniform: current unlearning methods do not erase information from the representation, they apply an invertible linear distortion that hides it from one particular prediction head. We propose One-Point Contraction (OPC), an unlearning objective that collapses forget-set features to the origin while leaving the retain-set geometry intact. We prove that this contraction is equivalent to driving the predictive distribution to maximum entropy, so the same mechanism delivers behavioral forgetting and representation-level erasure at once. Forgotten queries land in a region the network treats as out-of-distribution, and the gradient signal on those queries collapses along with their features. OPC is the only method in our benchmark that survives FM-recovery, resists relearning and gradient-inversion attacks, and decouples forget from retain features in entangled settings, all without sacrificing retain or test accuracy.

arXiv

VIBE: Vector Index Benchmark for Embeddings

Elias Jääsaari, Ville Hyvönen, Matteo Ceccarello, Teemu Roos, Martin Aumüller

Approximate nearest neighbor (ANN) search is a performance-critical component of many machine learning pipelines, and rigorous benchmarking is essential for assessing the performance of vector indexes for ANN search. However, the datasets of existing benchmarks no longer represent modern ANN applications, creating a need for an up-to-date benchmark. To address this gap, we introduce Vector Index Benchmark for Embeddings (VIBE), an open-source framework for benchmarking ANN algorithms. VIBE provides a pipeline for generating benchmark datasets with dense embedding models representative of modern applications, including retrieval-augmented generation (RAG). To represent real-world workloads, we also include out-of-distribution (OOD) datasets where the queries and the corpus are drawn from different distributions. These include multimodal retrieval datasets and maximum inner product search (MIPS) datasets covering two recent use cases: approximate attention computation and reductions of multi-vector retrieval to single-vector MIPS. We use VIBE to conduct a comprehensive evaluation of 22 open-source vector-index implementations across 11 in-distribution and 8 out-of-distribution datasets. The benchmark is available at https://github.com/vector-index-bench/vibe

arXiv

Beyond Either-Or Reasoning: Transduction and Induction as Cooperative Problem-Solving Paradigms

Janis Zenkner, Tobias Sesterhenn, Christian Bartelt

Traditionally, in Programming-by-example (PBE) the goal is to synthesize a program from a small set of input-output examples. Lately, PBE has gained traction as a few-shot reasoning benchmark, relaxing the requirement to produce a program artifact altogether which allows transductive methods to directly the missing output sample. Transduction and induction are complementary reasoning modes--where induction derives general rules from examples, transduction leverages the examples directly to infer specific outputs without intermediate generalization. Yet existing approaches either treat them as mutually exclusive or couple them in hybrid structures where one paradigm dictates a fixed trajectory for the other -- undermining the latter's reasoning potential and creating cascading errors. We move away from these hierarchical models and introduce cooperative transductive-inductive problem solving: by interleaving both reasoning modes and ensuring neither unconditionally dominates the other, we preserve the search autonomy and reasoning capacity of each paradigm. We instantiate this concept in TIIPS. Across three PBE domains, TIIPS consistently outperforms state-of-the-art baselines and generates programs that more closely mirror ground-truth trajectories in both syntax and semantics, indicating a better match to the intended program behavior. Our findings highlight cooperative reasoning as a promising new direction for harnessing the full power of symbolic, inductive and neural, transductive reasoning.

arXiv

When Search Teaches Style: Causal Internalization of Tactical Priors in AlphaZero

Ruitong Li, Binjie Guo, Aisheng Mo, Guowei Su, Han Wang, Jie Li, Ru Zhang

AlphaZero is normally evaluated as one agent: a policy-value network fused with Monte Carlo tree search. That fusion hides a causal question. When self-play search is given a useful prior, does the network absorb the induced behavior, or does the behavior stay rented from search at test time? We answer with Cross-Phase Prior Intervention (CPI), which switches a root-level tactical prior on and off independently during training and during evaluation, separating the prior's online effect from the learned residual it leaves in the weights. The endpoint is deliberately narrow: how often a network discharges a forced defensive obligation when no search-time guidance is available. On a sealed one-shot final test in 9x9 Gomoku and 19x19 Go, deleting the prior still leaves a large residual response rises from 13.8% to 26.3% in Gomoku and from 0.6% to 33.8% in Go-and soft reweighting teaches as well as hard action restriction, so pruning legal actions is not the mechanism. The same cross bounds the claim: re-enabling the prior restores nearly 100% response, leaving dependence gaps of 73.7 and 65.8 points. A latched-position evaluation localizes the residual to trained geometry-absent at the shared initialization, emerging over training, worth +17.3 points on in-distribution defenses but only +1.3 on structurally novel ones. Search is therefore best read as a training-time behavioral curriculum whose lessons are real, partial, and geometry-bound, and online competence and internalized competence are different estimands that a diagonal ablation cannot tell apart.

arXiv

Improving Sample Efficiency in Multi-Agent Reinforcement Learning for Simulated Football Games via Exploration

Amir Baghi, Jens Sjölund, Joakim Bergdahl, Linus Gisslén, Alessandro Sestini

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time, which inhibits their application for game-AI in standard game development. For instance, the state-of-the-art method TiZero takes 40 days to train high-quality policies for a football environment. In this paper, we hypothesize that better exploration mechanisms can improve the sample efficiency of multi-agent methods. Thereby, we propose utilizing a random network distillation bonus within the multi-agent TiZero framework, aiming to promote exploration. Additionally, we introduce architectural modifications to the original algorithm to enhance TiZero's computational efficiency. We evaluate the sample efficiency of our approach against original TiZero through extensive experiments. Our results show that random network distillation improves the sample efficiency per training phase by 13.3% compared with the original TiZero, enhancing generalization and adaptability to previously difficult scenarios. This highlights the better applicability of our variant in practical game development settings. Lastly, we qualitatively evaluate the gameplay of the produced models against a heuristic AI. We find that random network distillation leads to a higher accuracy in shooting, and it achieves higher behavioral stability as shown by the lower standard deviation achieved in gameplay metrics. The code is available at https://github.com/electronicarts/marling.

arXiv

Strong bounds for large-scale Minimum Sum-of-Squares Clustering

Anna Livia Croella, Veronica Piccialli, Antonio M. Sudoso

Clustering is a fundamental technique in data analysis and machine learning, used to group similar data points together. Among various clustering methods, the Minimum Sum-of-Squares Clustering (MSSC) is one of the most widely used. MSSC aims to minimize the total squared Euclidean distance between data points and their corresponding cluster centroids. Due to the unsupervised nature of clustering, achieving global optimality is crucial, yet computationally challenging. The complexity of finding the global solution increases exponentially with the number of data points, making exact methods impractical for large-scale datasets. Even obtaining strong lower bounds on the optimal MSSC objective value is computationally prohibitive, making it difficult to assess the quality of heuristic solutions. We address this challenge by introducing a novel method to validate heuristic MSSC solutions through optimality gaps. Our approach employs a divide-and-conquer strategy, decomposing the problem into smaller instances that can be handled by an exact solver. The decomposition is guided by an auxiliary optimization problem, the "anticlustering problem", for which we design an efficient heuristic. Computational experiments demonstrate the effectiveness of the method for large-scale instances, achieving optimality gaps below 3% while maintaining reasonable computational times. These results highlight the practicality of our approach in assessing feasible clustering solutions for large datasets, bridging a critical gap in MSSC evaluation.

arXiv

Prediction-Enhanced Monte Carlo: A Machine Learning View on Control Variate

Fengpei Li, Haoxian Chen, Jiahe Lin, Arkin Gupta, Xiaowei Tan, Honglei Zhao, Gang Xu, Yuriy Nevmyvaka, Agostino Capponi, Henry Lam

For many complex simulation tasks spanning areas such as healthcare, engineering, and finance, Monte Carlo (MC) methods are invaluable due to their unbiased estimates and precise error quantification. Nevertheless, Monte Carlo simulations often become computationally prohibitive, especially for nested, multi-level, or path-dependent evaluations lacking effective variance reduction techniques. While machine learning (ML) surrogates appear as natural alternatives, naive replacements typically introduce unquantifiable biases. We address this challenge by introducing Prediction-Enhanced Monte Carlo (PEMC), a framework that leverages modern ML models as learned predictors, using cheap and parallelizable simulation as features, to output unbiased evaluation with reduced variance and runtime. PEMC can also be viewed as a "modernized" view of control variates, where we consider the overall computation-cost-aware variance reduction instead of per-replication reduction, while bypassing the closed-form mean function requirement and maintaining the advantageous unbiasedness and uncertainty quantifiability of Monte Carlo. We illustrate PEMC's broader efficacy and versatility through three examples: first, equity derivatives such as variance swaps under stochastic local volatility models; second, interest rate derivatives such as swaption pricing under the Heath-Jarrow-Morton (HJM) interest-rate model. Finally, we showcase PEMC in a socially significant context - ambulance dispatch and hospital load balancing - where accurate mortality rate estimates are key for ethically sensitive decision-making. Across these diverse scenarios, PEMC consistently reduces variance while preserving unbiasedness, highlighting its potential as a powerful enhancement to standard Monte Carlo baselines.

arXiv

Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds

Shuhai Zhang, Jiahao Yang, Hui Luo, Jie Chen, LI Wang, Feng Liu, Bo Han, Mingkui Tan

Deep neural networks (DNNs) are vulnerable to adversarial samples crafted by adding imperceptible perturbations to clean data, potentially leading to incorrect and dangerous predictions. Adversarial purification has been an effective means to improve DNNs robustness by removing these perturbations before feeding the data into the model. However, it faces significant challenges in preserving key structural and semantic information of data, as the imperceptible nature of adversarial perturbations makes it hard to avoid over-correcting, which can destroy important information and degrade model performance. In this paper, we break away from traditional adversarial purification methods by focusing on the clean data manifold. To this end, we reveal that samples generated by a well-trained generative model are close to clean ones but far from adversarial ones. Leveraging this insight, we propose Consistency Model-based Adversarial Purification (CMAP), which optimizes vectors within the latent space of a pre-trained consistency model to generate samples for restoring clean data. Specifically, 1) we propose a Perceptual consistency restoration mechanism by minimizing the discrepancy between generated samples and input samples in both pixel and perceptual spaces. 2) To maintain the optimized latent vectors within the valid data manifold, we introduce a Latent distribution consistency constraint strategy to align generated samples with the clean data distribution. 3) We also apply a Latent vector consistency prediction scheme via an ensemble approach to enhance prediction reliability. CMAP fundamentally addresses adversarial perturbations at their source, providing a robust purification. Extensive experiments on CIFAR-10 and ImageNet-100 show that our CMAP significantly enhances robustness against strong adversarial attacks while preserving high natural accuracy.

arXiv

Efficient quantum-enhanced classical simulation for patches of quantum landscapes

Sacha Lerch, Ricard Puig, Manuel S. Rudolph, Armando Angrisani, Tyson Jones, M. Cerezo, Supanut Thanasilp, Zoë Holmes

Understanding the capabilities of classical simulation methods is key to identifying where quantum computers are advantageous. Not only does this ensure that quantum computers are used only where necessary, but also one can potentially identify subroutines that can be offloaded onto a classical device. In this work, we show that it is always possible to generate a classical surrogate of a sub-region (dubbed a "patch") of an expectation landscape produced by a parameterized quantum circuit. That is, we provide a quantum-enhanced classical algorithm which, after simple measurements on a quantum device, allows one to classically simulate approximate expectation values of a subregion of a landscape. We provide time and sample complexity guarantees for a range of families of circuits of interest, and further numerically demonstrate our simulation algorithms on an exactly verifiable simulation of a Hamiltonian variational ansatz and long-time dynamics simulation on a 127-qubit heavy-hex topology.

arXiv

Reconsidering the Energy Efficiency of Spiking Neural Networks Inference from Analytical Perspectives

Zhanglu Yan, Zhenyu Bai, Kaiwen Tang, Weng-Fai Wong

Spiking Neural Networks (SNNs) promise higher energy efficiency over conventional Quantized Artificial Neural Networks (QNNs) due to their event-driven, spike-based computation. However, prevailing energy evaluations often oversimplify, focusing on computational aspects while neglecting critical overheads like comprehensive data movements and memory accesses. Such simplifications can lead to misleading conclusions regarding the true energy benefits of SNNs. This paper presents a rigorous re-evaluation. We establish a fair baseline by mapping rate-encoded SNNs with $T$ timesteps to capacity-matched QNNs with $\lceil \log_2(T+1) \rceil$ bits. This ensures both models have comparable representational capacities, as well as similar hardware requirements, enabling meaningful energy comparisons. We introduce a detailed analytical energy model encompassing core computation and data movements. Using this model, we systematically explore a wide parameter space, including intrinsic network characteristics (SNN time window size, spike rate, QNN sparsity, model size, weight bit-level) and hardware characteristics (memory system and network-on-chip). Our analysis identifies specific operational regimes where SNNs genuinely offer superior energy efficiency. For example, under typical neuromorphic hardware conditions, SNNs with moderate time windows ($T = 5$) require an average spike rate ($s_r$) below 5.7% to outperform equivalent QNNs These insights guide the design of truly energy-efficient neural network solutions.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.