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

CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation

Gengyu Zhan

Large language models (LLMs) can summarize heterogeneous user evidence in natural language, but current LLM recommenders often collapse enduring preferences, transient intent, and exposure-induced behavior into one profile. This makes recommendation vulnerable to feedback loops: repeated exposure is mistaken for preference, immediate clicks dominate delayed satisfaction, and fluent explanations need not reflect the ranking decision. We propose our method, a model-agnostic framework for long-horizon recommendation. Our method uses a frozen multimodal language model to convert item content and feedback into evidence-grounded semantic atoms, then maintains separate short-term, long-term, and exposure memories. Propensity-weighted updates reduce policy-induced exposure bias, while a conservative offline critic reranks candidates for delayed satisfaction under a behavior-support constraint. Explanations use only influential evidence atoms and are checked by counterfactual deletion. We provide an identification result and evaluate the framework in e-commerce-like, news-like, and short-video-like environments. Across ten seeds, our method improves discounted long-term value over the strongest alternative by 6.1%, 7.6%, and 6.7%, respectively. Twenty-seed paired ablations show significant value drops after removing propensity correction (0.739 +/- 0.191) or conservative support regularization (0.523 +/- 0.234). A frozen instruction language model also more than doubles semantic-atom NDCG over TF-IDF on a held-out paraphrase benchmark.

arXiv

When Rates Are Geometric: Rate-Certificate Transfer for Contact Splittings in Optimization

George A Kevrekidis

Discrete optimization algorithms are often analyzed through continuous-time limiting ODEs, but a convergence certificate for the ODE is not automatically one for the discrete algorithm. We develop contact Hamiltonian systems as a setting where the transfer can be made precise. A contact Hamiltonian $H$ on $J^1(\mathbb{R}^n)$ obeys the intrinsic decay identity $\dot H = -H\,\partial_s H$, so an augmented energy $\mathcal{E}$ built from $H$, together with the conformal rate $\partial_s H$, is a continuous-time rate certificate whenever $\mathcal{E}$ controls the objective gap. Our main theorem states, under three named and independently checkable hypotheses, that an order-$r$ contact splitting with step $h$ transfers this certificate over the finite horizon set by backward error analysis. The discrete decay envelope is governed by the modified conformal factor up to $O(h^r)$ perturbations plus a backward-error shadowing defect, and the mechanism is inherited exactly because the modified Hamiltonian is itself a contact Hamiltonian. Quadratic heavy ball is a fully solvable example: its projected dissipative-leapfrog spectrum agrees with established conformal-symplectic optimization theory, while the augmented contact Hamiltonian yields a sharp objective-to-certificate comparison that verifies the transfer hypotheses. For strongly convex objectives with state-dependent damping, an explicit Bregman-type Lyapunov certificate instead transfers by an auxiliary-shadowing corollary. The decomposition $H=K+V+D$ into kinetic, objective-encoding potential, and dissipation terms serves as a design template, with a catalogue of closed-form sub-flows including contact-specific damping families. Numerical experiments confirm the predicted conformal-factor tracking orders and show competitive performance on ill-conditioned benchmarks and deep-learning tasks.

arXiv

Extending Desbordante with Probabilistic Functional Dependency Discovery Support

Ilia Barutkin, Maxim Fofanov, Sergey Belokonny, Vladislav Makeev, George Chernishev

Data profiling aims to extract complex patterns from data for further analysis and use that data in domains such as data cleaning, data deduplication, anomaly detection, and many more. Functional dependencies (FDs) are one of the most well-known patterns. However, they are poorly suited for these tasks, as real data is usually dirty, and the rigid definition of FDs does not allow algorithms to locate them. For this reason, there are several formulations aimed at relaxing FDs to support dirty data, with approximate functional dependency (AFD) being the most popular one. Another formulation is the Probabilistic Functional Dependency (pFD), which we aim to support inside Desbordante - a science-intensive, high-performance and open-source data profiling tool implemented in C++. However, pFDs are relatively poorly studied, compared to AFDs. In this paper we study pFDs, both analytically and empirically. We start by assessing how different pFDs and AFDs are by studying cases in which pFDs have an edge over AFDs. Then, we implement the algorithm for pFD discovery, as well as study its run time and memory consumption. We also compare it with an AFD discovery algorithm. Lastly, we study the output of both algorithms to learn whether or not it is possible to use AFD discovery algorithm to get pFDs and vice versa.

arXiv

Variational-Ising-Attention (VIA):TailoredAttentionMattersfor Science

Rui Wang

Attention enables context modeling via query-key scoring with softmax normalization. Driven by industrial long-context demands, mainstream research has converged toward sparsity and efficiency--yet softmax's independence assumption persists. For scientific tasks unburdened by long-token constraints, however, richer structured coupling may often be essential, making tailored attention both viable and more appropriate. To this end, we propose Variational-Ising-Attention (VIA), which augments softmax normalization with an interacting Ising model; attention patterns emerge from learnable pairwise couplings via variational mean-field inference, redefining attention from a ranking over isolated items to a collective state over interacting entities. We instantiate VIA on retrosynthesis reaction center prediction, a task inherently governed by cooperative bond-breaking constraints. Comprehensive experiments across model variants, coupled with mechanistic analyses, demonstrate that VIA consistently and substantially outperforms standard softmax attention. More broadly, our findings suggest that for scientific problems, the optimal solution is not general-purpose efficiency, but appropriately tailored attention aligned with intrinsic domain structure. This work provides a theoretically grounded and empirically validated instantiation of this paradigm.

arXiv

Order in Desbordante: Techniques for Efficient Implementation of Order Dependency Discovery Algorithms

Yakov Kuzin, Dmitriy Shcheka, Michael Polyntsov, Kirill Stupakov, Mikhail Firsov, George Chernishev

Science-intensive data profiling focuses on discovery and validation of various patterns in datasets. This study considers discovery of one such pattern - order dependency (OD). Simply put, OD states that some list of columns is ordered according to another one. It is of use for database query optimization, data cleaning and deduplication, anomaly detection, and much more. Existing discovery methods have approached this problem solely from the algorithmic standpoint, without focusing on the implementation side. At the same time, this problem is very computationally intensive, and therefore this part should not be ignored, as it brings ODs closer to industrial use. In this paper, we study two algorithms for OD discovery which target different OD axiomatizations - FASTOD and ORDER. We start by reimplementing these algorithms in C++ in order to speed them up and lower their memory consumption. We then analyze their bottlenecks and propose several techniques which improve their performance even further. To perform evaluation, we have implemented these algorithms inside Desbordante - a science-intensive, high-performance, and open-source data profiling tool developed in C++. Experiments have demonstrated a performance improvement of up to 3x obtained by reimplemented versions, and, with the application of our techniques, up to 10x. Memory consumption has been lowered by up to 2.9x.

arXiv

Optimal Reward Shaping: Autonomous Car Parking Case Study

Emre Özkaya, Nicolas R. Gauger

Designing effective reward functions for model-free reinforcement learning under non-holonomic constraints remains a persistent challenge, often resulting in severe local minima such as policy paralysis or over-conservative hazard avoidance. In this work, we present a parameterized reward shaping framework featuring coverage-gated alignment feedback, drive-direction switch regularization, and an aligned episode termination mechanism evaluated on an autonomous parallel parking task. Crucially, we show that environmental reward parameters and algorithmic hyperparameters are deeply co-dependent, requiring joint meta-optimization to achieve stable convergence. By employing surrogate-based Bayesian optimization, our co-optimized Deep Q-Network (DQN) agent resolves characteristic control failure modes, significantly outperforming uncalibrated baselines across both success rate and trajectory smoothness.

arXiv

Restoration Flow Matching-Based Channel Refinement and Equalization Correction for MIMO Semantic Communications

Wenkai Liu, Nan Ma, Jianqiao Chen, Xiaodong Xu, Meixia Tao, Ping Zhang

In multiple-input multiple-output (MIMO) semantic communication, imperfect channel state information (CSI) and equalization mismatch can seriously degrade semantic reconstruction quality. To address this issue, we propose a unified restoration flow matching (RFM)-based framework for channel refinement and equalization correction. Specifically, the channel RFM (CRFM) module is developed to refine the coarse channel, thereby improving channel estimation accuracy. Based on the refined channel, the developed semantic RFM (SRFM) module is employed to correct the residual distortions in the post-equalization latent space. The key idea is to formulate the two cascaded inverse problems of channel estimation and equalization as the unified conditional restoration task, in which the learned conditional velocity field guides the perturbed distribution towards the target distribution. To enhance the robustness of these two modules under various distortion conditions, we develop a dual-anchor perturbation training strategy that jointly learns near-manifold refinement and large-error correction, and implement inference through a few-step deterministic ordinary differential equation (ODE) solver. Extensive experiments on MIMO channels and visual semantic transmission tasks demonstrate that the proposed scheme improves key metrics for channel estimation and semantic reconstruction quality. Moreover, compared with representative diffusion-based generative baselines, the proposed method requires fewer sampling steps.

arXiv

Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models

Liangyu Li, Qingwen Liu, Mingqing Liu

Controllers based on sampling and latent world models assign a predicted terminal cost to each candidate action sequence, choose the minimum, execute its first action block, and replan. This rule can fail even when the terminal cost perfectly and accurately reflects the true task objective in the physical world. Residual prediction error can give an infeasible sequence an anomalously low cost, and a larger proposal pool gives such errors more chances to outrank feasible alternatives. We call this conditional failure proposal overgeneration. In Cube candidate execution audits, increasing the total proposal budget from 72 to 288 reduces the feasibility of selection by minimum latent cost from .375 to .062 for position targets and from .344 to .031 for targets defined by position and yaw, although every larger pool contains a feasible sequence. We introduce Adjacent Set Action Reconstruction (ASAR). Among proposals with low cost, ASAR measures density from standardized early action prefixes and reconstructs a full sequence from an adjacent set with a light anchor from the sequence with minimum cost. On a Carry and Release evaluation set of 75 queries, Kernel ASAR improves event completion success over matching selection by 28.0, 24.0, and 18.7 percentage points under latent cost and by 18.7, 20.0, and 17.3 points under a trajectory reachability cost at 72, 144, and 288 proposals. Analysis of finite proposal pools characterizes selection risk from the lower tail, separation by a related radius support statistic, and sequence containment under an explicit local feasibility condition.

arXiv

Anticipatory Risk-Guided Reinforcement Learning for Safe Flight Through Dynamic Clutter

Yuchao Mei, Guohao Zhang, Luxia Ai, Haopeng Chen, Wenbing Tao

Safe quadrotor navigation in cluttered and dynamic environments depends not only on instantaneous geometric perception, but more critically on anticipating collision risks induced by relative motion. Conventional modular pipelines frequently suffer from perception latency, while end-to-end learning methods relying on implicit scalar rewards often struggle to extract reliable spatio-temporal features without physics-grounded supervision. To address this, we propose an anticipatory risk-guided reinforcement learning framework. Leveraging privileged simulator states, we construct a directionally aligned future collision risk map based on the Closest Point of Approach (CPA). Through an asymmetric actor-critic architecture, the network is trained to self-predict this structured risk, which explicitly guides the visual policy during deployment. A lightweight spatio-temporal encoder extracts motion cues directly from onboard depth sequences, bypassing explicit object tracking or optical flow estimation. Extensive simulated and real-world experiments demonstrate that our method effectively improves safety margins and flight efficiency in dense dynamic clutters compared to existing baselines. Furthermore, the learned policy achieves robust zero-shot Sim-to-Real transfer on a physical quadrotor, relying purely on abstracted spatio-temporal depth sequences and its self-predicted risk priors, validating the effectiveness of our approach and its robust generalization from simulation to reality.

arXiv

Random Forest-Based Prediction of Bone Volume Fraction and Fracture Position from S-Parameters

Jianhe Li, Jinsui Meng, Yida Zhao, Zihe Wang, Liaoran Sun, Tao Shan

In this paper, we propose a method for predicting bone volume fraction (BVF) and fracture position by constructing a random forest model based on multichannel S-parameters. A nine-antenna microwave scanning system is designed and fabricated to acquire the multichannel S-parameter data. Bone-mimicking phantoms are developed, and corresponding experiments are conducted to validate the effectiveness of the proposed approach. Both synthetic and experimental results demonstrate the validity of the method.

arXiv

Neonatal Hypoxic-ischaemic Encephalopathy Classification from the EEG and HRV Signals Using a Conformer based Masked Autoencoder

Shuwen Yu, William P Marnane, Geraldine B. Boylan, Gordon Lightbody

In this paper, we propose the MAEConformer, a novel self-supervised learning framework that combines the Conformer architecture with the Masked Autoencoder (MAE) paradigm for large-scale representation learning from unlabelled electroencephalography (EEG) and heart rate variability (HRV) signals. By integrating convolutional operations with Transformer-based self-attention, MAEConformer effectively captures both local temporal patterns and long-range contextual dependencies in physiological time series. To enhance reconstruction fidelity and representation quality, a multi-resolution short-time Fourier transform (MR-STFT) loss is incorporated alongside the reconstruction objective, enabling the model to jointly learn temporal and spectral characteristics across multiple scales. Modality-specific EEG and HRV MAEConformer models were pretrained on 6,030h and 4,868h of unlabelled recordings, respectively, and subsequently transferred to expert-annotated downstream tasks. Experimental results demonstrate that the learned representations provide strong transferability and data efficiency. In EEG-based hypoxic ischemic encephalopathy (HIE) severity classification, the pretrained MAE-EEG model achieved test AUCs of 97.19% and 96.56% for binary and four-class classification tasks, respectively, outperforming a range of state-of-the-art supervised and self-supervised baselines. On the HRV-based HIE severity classification task, MAE-HRV achieved a test AUC of 82.42%, surpassing both self-supervised Transformer-based and supervised convolutional baselines. These findings demonstrate the effectiveness of MAEConformer for learning robust and transferable representations across multiple physiological modalities.

arXiv

Topological Data Analysis and Graph-Theoretic Approaches for Tennis Match Prediction

Jake Schwaderer, Alexander Bastien, Omid Khormali, Alejandro Navarrete, Mia Pesavento, Angelika Elderbrook

We present two approaches for predicting tennis match outcomes using topological data analysis and graph theory on ATP singles matches from 2000-2025. The first method applies lower-star filtration to player competitive networks, extracting topological features through persistent homology using four summary methods (VAB, HNAV, HWNAV, OW-HNPV) combined with Modified Band Depth analysis. Algorithmic optimizations including ego graph approximations and triangle elimination enable analysis of about 66k matches. Our Random Forest model achieves 66.2% accuracy (AUC = 0.719) using topological, graph-theoretic, and ranking features. Feature importance analysis reveals that rankings contribute 36.3%, centralities 25.5%, and TDA features 24.0%, with topological features providing complementary signal. When rankings are unavailable, the topology-only model maintains 63.56% accuracy, demonstrating that network-derived features alone capture meaningful competitive structure. The second method uses a modified Katz similarity index with temporal edge weighting, achieving 62.48% accuracy on held-out test data. This work represents the first application of lower-star filtration to tennis prediction, provides systematic comparison of four topological summary methods in sports analytics, and demonstrates that TDA can achieve above-chance prediction using network topology alone while providing additional value when combined with traditional features.

arXiv

Impute On-Demand: Adaptive Correlated Time Series Imputation for Changing Environments

Zhichen Lai, Huan Li, Dalin Zhang, Dong Gong, Lina Yao, Christian S. Jensen

Internet of Things (IoT) applications generate vast amounts of Correlated Time Series (CTS) data that often contain missing values and require imputation. Existing methods emphasize accuracy but often lack adaptability to changing IoT environments: they are vulnerable to sensor failures, cannot selectively impute only incomplete sensors, and use static architectures that do not adapt to resource availability. To address these limitations, we propose AdaCTSi, an adaptive CTS imputer for changing environments. AdaCTSi combines a One-shot Temporal Convolutional Network with a Learned Time-Sensor Index Table to extract and decouple complex spatio-temporal features into sensor-wise embeddings, enabling adaptation to varying sensor subsets. Sparse Spatial Attention efficiently extracts dynamic spatial correlations, while Correlation-Weighted Sensor Selection selects informative sensors to provide sufficient spatial context. Experiments with twelve baseline methods, three adaptability scenarios, and five benchmark datasets covering traffic, air quality, and trajectory data show that AdaCTSi reduces MAE by an average of 33.1% relative to the strongest baseline on each dataset. A single trained model supports sensor-subset and resource-adaptive inference, and its modest memory footprint enables deployment on commodity computing devices, including MCUs.

arXiv

Learning switched non-linear dynamical systems from a single trajectory

Sunny G. W. Wang, Hemant Tyagi

We study empirical risk minimization for learning non-linear dynamical systems whose transition dynamics may switch over time. Under stability assumptions, and i.i.d switching over a set of $K$ modes, we derive non-asymptotic bounds on the prediction risk expressed in terms of the metric entropy of the underlying function class. We instantiate our general result for Hölder and linear function classes, obtaining explicit convergence rates that depend on the effective sample size $Tp_i$, where $T$ is the trajectory length and $p_i$ is the probability of observing mode $i$. Numerical simulations support our theoretical findings. To the best of our knowledge, these results are the first non-asymptotic guarantees for learning switched nonlinear dynamical systems from a single trajectory.

arXiv

Physics-Informed Neural Networks for Discovering Periodic Orbits in the Gravitational Three-Body Problem

Nikolaos Kollias, Nikolaos Matzakos

Locating periodic solutions of chaotic dynamical systems normally requires an initial guess close enough to the target orbit for numerical continuation or gradient-based search to converge. We show that Physics-Informed Neural Networks (PINNs) trained on sparse, noisy observations \emph{without} initial conditions recover periodic orbits of the gravitational three-body problem, including orbit families absent from the training data. The method rests on a second-order ODE formulation, fixed-frequency Fourier features, percentile-based adaptive refinement, and a trainable scaling parameter, each validated on forward problems. Across two 100-seed ensembles, $23$--$25\%$ of runs converge to families not present in the training data. We then ask what determines which family emerges. Two $χ^2$ tests give a consistent answer: changing the training data source significantly shifts the distribution of recovered families ($p < 0.001$, Cramér's $V = 0.339$), whereas switching between the two initialization distributions tested does not ($p = 0.620$, $V = 0.094$). The random seed selects which family a given run recovers; the \emph{distribution} the weights are drawn from does not shift the aggregate frequencies, but the training data does. The evidence is empirical: we do not characterize the loss landscape analytically, and PINNs remain slower than conventional integrators on well-posed initial-value problems. What the experiments establish is that the recovered orbits are verifiable rather than merely plausible: the identified ones refine to genuine periodic solutions, a network trained on Lagrange data recovers the figure-eight choreography (Li--Liao class I.A.1, matched to seven significant digits in $T^*$), and one trained on figure-eight data recovers a Broucke--Hadjidemetriou--Hénon orbit closing to $δ_T < 10^{-9}$.

arXiv

An adaptive multi-fuzzy logic model for diagnosing transformer faults using dynamic weight optimization

Kim-Anh Nguyen, Huy Hoang Le, Ba Tu Phung

Dissolved gas analysis (DGA) is crucial for diagnosing early power transformer failures. Traditional DGA interpretation methods like Duval Triangle, IEC ratio, Roger ratio, Doernenburg ratio and Key Gas are inconsistent and vary in accuracy, especially for multiple fault conditions. We propose an Adaptive Multi-Fuzzy Logic (AMFL) model integrating multiple DGA methods with fuzzy logic and a dynamic weight adjustment mechanism. Unlike existing approaches with fixed weights, this system iteratively evaluates each method's diagnostic performance, identifies multiple fault types, and adjusts weights based on fault prediction accuracy. A feedback-based optimization recalibrates weights after each cycle to ensure optimal solution convergence. The model, implemented in MATLAB/Simulink, is validated against DGA datasets with known error conditions. Results show the AMFL model significantly improves diagnostic accuracy, especially in complex error scenarios, and enhances adaptability to new datasets. Comparative analysis demonstrates the proposed method outperforms traditional fixed weight multi-fuzzy systems in accuracy, consistency, and reliability of error detection. This work provides a robust, flexible diagnostic tool for transformer condition monitoring and supports more accurate asset management decisions.

arXiv

Charging Phase Health Indicators for Battery State-of-Health Estimation: A Systematic Comparison of CC, CV, and Combined Approaches under Cross-Battery Validation

Huy Hoang Le, Kim-Anh Nguyen

Accurate State-of-Health estimation is essential for safe battery operation and cost-effective maintenance. Although numerous health indicators have been derived from constant-current (CC) and constant-voltage (CV) charging phases, their effectiveness under realistic cross-battery validation remains insufficiently studied. This work addresses this gap through a systematic comparison of CC-only, CV-only, and combined indicator sets using rigorous Leave-One-Battery-Out (LOBO) validation on the NASA battery aging dataset. Four CV-phase indicators and CC phase duration are evaluated individually and in combination. Results show that the combined CC+CV approach achieves the best performance (R2 = 0.874), confirming that CC and CV phases capture complementary degradation information. Moreover, a 119% performance gap is observed between standard 5-fold cross-validation and LOBO validation, indicating that conventional evaluation overestimates practical accuracy. Based on these findings, practical guidelines are provided for indicator selection under data and computational constraints.

arXiv

A Multi-stage Constrained Optimization Framework for Data-driven Problems

Ye Shi

Variational autoencoders (VAEs) transform high-dimensional, often noisy data into a compact latent representation, making downstream optimization more tractable. Three challenges persist in VAE-based constrained optimization: (i) sampling effectively within the latent space, (ii) identifying the active decision variables that actually influence the objective and constraints, and (iii) enforcing constraints without destabilizing training. We propose a Multi-stage Constrained Optimization Framework (MCOF). First, an entropy-constrained VAE (EC-VAE) coupled with a feature selector embeds objective and constraint information into a designated subset of latent variables, so that optimization proceeds over a low-dimensional subspace while the remaining coordinates supply solution diversity. Second, a Uniform Transformation (UT) module applies a per-dimension probability integral transform, replacing the irregular aggregate posterior with a uniform distribution over a bounded box and mitigating posterior collapse and Gaussian mixture bias. Third, a constraint-priority filter method (CPFM) solves the resulting surrogate problem by alternating violation-reduction and objective-reduction steps under a filter acceptance test, returning solutions that are feasible for the learned surrogate to a specified tolerance without requiring multiplier estimation. Finally, unselected latent coordinates are resampled to generate diverse decodings of a single optimized solution. We validate MCOF on a synthetic problem, where we ablate each stage and recover the analytic optimum, and on a ZINC250k drug design task, where the generated molecules satisfy the imposed constraints and are entirely novel relative to the training set.

arXiv

ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour

Jianhang Xie, Sicheng Tan, Vishnu Naresh Boddeti, Zhichao Lu

Fully homomorphic encryption (FHE) provides strong cryptographic guarantees for private inference, but deploying transformer models under FHE remains prohibitively expensive. A key bottleneck is that non-linear operations such as softmax, normalization, and activation must be replaced with polynomial approximations compatible with the CKKS scheme, and the multiplicative depth consumed by these approximations dominates inference cost. Recent frameworks have advanced approximation techniques, yet all rely on manually configured approximation hyperparameters (e.g., number of iterations, polynomial degree), applied uniformly across all layers. While convenient, this uniform-configuration approach is overly rigid: different layers can tolerate different levels of approximation error without degrading predictive accuracy, and uniform configurations cannot exploit this variability to reduce latency. Allowing each layer to adopt its own configuration, however, causes the search space to explode with model depth, reaching roughly $10^{84}$ configurations for BERT/ViT (12 layers) and $10^{225}$ for LLaMA3 (32 layers), rendering manual exploration practically impossible. We present ATLAS, an automated framework that configures per-layer approximation settings by formulating the problem as a multi-objective optimization over latency and predictive accuracy. The resulting problem is inherently difficult: 1) competing objectives over a large decision space (120 or 320 variables for BERT/ViT or LLaMA3); 2) expensive evaluation, as each configuration takes 70-1,000 seconds even in cleartext; and 3) sparse optimization signals, as 35-50% of candidate configurations yield numerically invalid solutions. ATLAS addresses these challenges through a two-stage optimization strategy that progressively relaxes layer-wise constraints, combined with surrogate models to accelerate evaluation.

arXiv

Sparse Gaussian-Mixture-Model Q-Functions via Hadamard Overparametrization for Online Reinforcement Learning

Minh Vu, Konstantinos Slavakis

This paper develops an online, off-policy policy-iteration framework for reinforcement learning (RL), based on sparse Gaussian-mixture-model Q-functions (S-GMM-QFs). The framework reconciles streaming, non-stationary data with the Riemannian structure of the parameter space while handling distributional mismatch through experience replay. S-GMM-QFs are introduced via Hadamard overparametrization, enabling interpretable sparsification through smooth regularization that facilitates Riemannian-based optimization. Overparametrization allows the framework to adaptively identify meaningful components from a large initial pool, yielding sparse models where interpretability emerges naturally from geometry: each component's parameters (means and covariances) explicitly encode its geometric role in the ambient state-action space. These geometric roles are learned through online gradient descent on a smooth objective over a (Cartesian-product) Riemannian manifold. Numerical tests demonstrate that S-GMM-QFs match or exceed deep RL methods while using substantially fewer parameters and achieving faster improvement per observed transition. Notably, parameter efficiency and interpretability combine to maintain strong generalization in low-parameter regimes where sparsified deep RL approaches degrade.

Keep browsing

More papers from top AI conferences

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