ICML 2024 论文列表

An emergency responder management (ERM) system dispatches responders, such as ambulances, when it receives requests for medical aid. ERM systems can also proactively reposition responders between predesignated waiting locations to cover any gaps that arise due to the prior dispatch of responders or significant changes in the distribution of anticipated requests. Optimal repositioning is computationally challenging due to the exponential number of ways to allocate responders between locations and the uncertainty in future requests. The state-of-the-art approach in proactive repositioning is a hierarchical approach based on spatial decomposition and online Monte Carlo tree search, which may require minutes of computation for each decision in a domain where seconds can save lives. We address the issue of long decision times by introducing a novel reinforcement learning (RL) approach, based on the same hierarchical decomposition, but replacing online search with learning. To address the computational challenges posed by large, variable-dimensional, and discrete state and action spaces, we propose: (1) actor-critic based agents that incorporate transformers to handle variable-dimensional states and actions, (2) projections to fixed-dimensional observations to handle complex states, and (3) combinatorial techniques to map continuous actions to discrete allocations. We evaluate our approach using real-world data from two U.S. cities, Nashville, TN and Seattle, WA. Our experiments show that compared to the state of the art, our approach reduces computation time per decision by three orders of magnitude, while also slightly reducing average ambulance response time by 5 seconds.

It has long been challenging to recover the underlying dynamic 3D scene representations from a monocular RGB video. Existing works formulate this problem into finding a single most plausible solution by adding various constraints such as depth priors and strong geometry constraints, ignoring the fact that there could be infinitely many 3D scene representations corresponding to a single dynamic video. In this paper, we aim to learn all plausible 3D scene configurations that match the input video, instead of just inferring a specific one. To achieve this ambitious goal, we introduce a new framework, called OSN. The key to our approach is a simple yet innovative object scale network together with a joint optimization module to learn an accurate scale range for every dynamic 3D object. This allows us to sample as many faithful 3D scene configurations as possible. Extensive experiments show that our method surpasses all baselines and achieves superior accuracy in dynamic novel view synthesis on multiple synthetic and real-world datasets. Most notably, our method demonstrates a clear advantage in learning fine-grained 3D scene geometry.

To mitigate the computational complexity in the self-attention mechanism on long sequences, linear attention utilizes computation tricks to achieve linear complexity, while state space models (SSMs) popularize a favourable practice of using non-data-dependent memory pattern, *i.e.,* emphasize the near and neglect the distant, to processing sequences. Recent studies have shown the priorities by combining them as one. However, the efficiency of linear attention remains only at the theoretical level in a causal setting, and SSMs require various designed constraints to operate effectively on specific data. Therefore, in order to unveil the true power of the hybrid design, the following two issues need to be addressed: (1) hardware-efficient implementation for linear attention and (2) stabilization of SSMs. To achieve this, we leverage the thought of tiling and hierarchy to propose CHELA (short-long Convolutions with Hardware-Efficient Linear Attention), which replaces SSMs with short-long convolutions and implements linear attention in a divide-and-conquer manner. This approach enjoys global abstraction and data-dependent selection from stable SSM and linear attention while maintaining real linear complexity. Our comprehensive experiments on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method.

The autoregressive nature of conventional large language models (LLMs) inherently limits inference speed, as tokens are generated sequentially. While speculative (Leviathan et al., 2023) and parallel (Stern et al., 2018) decoding techniques attempt to mitigate this, they face limitations: either relying on less accurate smaller models for generation or failing to fully leverage the base LLM's representations. We introduce a novel architecture, Tandem transformers, to address these issues. This architecture uniquely combines (1) a small autoregressive model and (2) a large model operating in block mode (processing multiple tokens simultaneously). The small model's predictive accuracy is substantially enhanced by granting it attention to the large model's richer representations. On the PaLM2 pretraining dataset, a tandem of PaLM2-Bison and PaLM2-Gecko demonstrates a 3.3% improvement in next-token prediction accuracy over a standalone PaLM2-Gecko, offering a 1.16x speedup compared to a PaLM2-Otter model with comparable downstream performance. We further incorporate the Tandem model within the speculative decoding (SPEED) framework where the large model validates tokens from the small model. This ensures that the tandem of PaLM2-Bison and PaLM2-Gecko achieves substantial speedup (around 1.14x faster than using vanilla PaLM2-Gecko in SPEED) while maintaining identical downstream task accuracy.

Reasoning from sequences of raw sensory data is a ubiquitous problem across fields ranging from medical devices to robotics. These problems often involve using long sequences of raw sensor data (e.g. magnetometers, piezoresistors) to predict sequences of desirable physical quantities (e.g. force, inertial measurements). While classical approaches are powerful for locally-linear prediction problems, they often fall short when using real-world sensors. These sensors are typically non-linear, are affected by extraneous variables (e.g. vibration), and exhibit data-dependent drift. For many problems, the prediction task is exacerbated by small labeled datasets since obtaining ground-truth labels requires expensive equipment. In this work, we present Hierarchical State-Space models (HiSS), a conceptually simple, new technique for continuous sequential prediction. HiSS stacks structured state-space models on top of each other to create a temporal hierarchy. Across six real-world sensor datasets, from tactile-based state prediction to accelerometer-based inertial measurement, HiSS outperforms state-of-the-art sequence models such as causal Transformers, LSTMs, S4, and Mamba by at least 23% on MSE. Our experiments further indicate that HiSS demonstrates efficient scaling to smaller datasets and is compatible with existing data-filtering techniques. Code, datasets and videos can be found on https://hiss-csp.github.io.

Neural Language Models (LMs) offer an exciting solution for general-purpose embodied control. However, a key technical issue arises when using an LM-based controller: environment observations must be converted to text, which coupled with history, results in long and verbose textual prompts. As a result, prior work in LM agents is limited to restricted domains with small observation size as well as minimal needs for interaction history or instruction finetuning. In this paper, we introduce diff history, a simple and highly effective solution to these issues. By applying the Unix diff command on consecutive text observations in the interaction histories used to prompt LM policies, we can both abstract away redundant information and focus the content of textual inputs on the salient changes in the environment. On NetHack, an unsolved video game that requires long-horizon reasoning for decision-making, LMs tuned with diff history match state-of-the-art performance for neural agents while needing 1800X fewer training examples compared to prior work. Even on the simpler BabyAI-Text environment with concise text observations, we find that although diff history increases the length of prompts, the representation it provides offers a 25% improvement in the efficiency of low-sample instruction finetuning. Further, we show that diff history scales favorably across different finetuning dataset sizes. We open-source our code and data to https://diffhistory.github.io.

Backdoor defense is crucial to ensure the safety and robustness of machine learning models when under attack. However, most existing methods specialize in either the detection or removal of backdoors, but seldom both. While few works have addressed both, these methods rely on strong assumptions or entail significant overhead costs, such as the need of task-specific samples for detection and model retraining for removal. Hence, the key challenge is how to reduce overhead and relax unrealistic assumptions. In this work, we propose two Energy-Based BAckdoor defense methods, called EBBA and EBBA+, that can achieve both backdoored model detection and backdoor removal with low overhead. Our contributions are twofold: First, we offer theoretical analysis for our observation that a predefined target label is more likely to occur among the top results for various samples. Inspired by this, we develop an enhanced energy-based technique, called EBBA, to detect backdoored models without task-specific samples (i.e., samples from any tasks). Secondly, we theoretically analyze that after data corruption, the original clean label of a poisoned sample is more likely to be predicted as a top output by the model, a sharp contrast to clean samples. Accordingly, we extend EBBA to develop EBBA+, a new transferred energy approach to efficiently detect poisoned images and remove backdoors without model retraining. Extensive experiments on multiple benchmark datasets demonstrate the superior performance of our methods over baselines in both backdoor detection and removal. Notably, the proposed methods can effectively detect backdoored model and poisoned images as well as remove backdoors at the same time.

In the evolving landscape of natural language processing (NLP), fine-tuning pre-trained Large Language Models (LLMs) with first-order (FO) optimizers like SGD and Adam has become standard. Yet, as LLMs grow in size, the substantial memory overhead from back-propagation (BP) for FO gradient computation presents a significant challenge. Addressing this issue is crucial, especially for applications like on-device training where memory efficiency is paramount. This paper proposes a shift towards BP-free, zeroth-order (ZO) optimization as a solution for reducing memory costs during LLM fine-tuning, building on the initial concept introduced by (Malladi et al., 2023). Unlike traditional ZO-SGD methods, ou让work expands the exploration to a wider array of ZO optimization techniques, through a comprehensive, first-of-its-kind benchmarking study across five LLM families, three task complexities, and five fine-tuning schemes. Our study unveils previously overlooked optimization principles, highlighting the importance of task alignment, the role of the forward gradient method, and the balance between algorithm complexity and fine-tuning performance. We further introduce novel enhancements to ZO optimization, including block-wise descent, hybrid training, and gradient sparsity. Our study offers a promising direction for achieving further memory-efficient LLM fine-tuning. Codes to reproduce all our experiments will be made public.

Modeling unsteady, fast transient, and advection-dominated physics problems is a pressing challenge for physics-aware deep learning (PADL). The physics of complex systems is governed by large systems of partial differential equations (PDEs) and ancillary constitutive models with nonlinear structures, as well as evolving state fields exhibiting sharp gradients and rapidly deforming material interfaces. Here, we investigate an inductive bias approach that is versatile and generalizable to model generic nonlinear field evolution problems. Our study focuses on the recent physics-aware recurrent convolutions (PARC), which incorporates a differentiator-integrator architecture that inductively models the spatiotemporal dynamics of generic physical systems. We extend the capabilities of PARC to simulate unsteady, transient, and advection-dominant systems. The extended model, referred to as PARCv2, is equipped with differential operators to model advection-reaction-diffusion equations, as well as a hybrid integral solver for stable, long-time predictions. PARCv2 is tested on both standard benchmark problems in fluid dynamics, namely Burgers and Navier-Stokes equations, and then applied to more complex shock-induced reaction problems in energetic materials. We evaluate the behavior of PARCv2 in comparison to other physics-informed and learning bias models and demonstrate its potential to model unsteady and advection-dominant dynamics regimes.

Model inversion, which aims to reconstruct the original training data from pre-trained discriminative models, is especially useful when the original training data is unavailable due to privacy, usage rights, or size constraints. However, existing dense inversion methods attempt to reconstruct the entire image area, making them extremely inefficient when inverting high-resolution images from large-scale Vision Transformers (ViTs). We further identify two underlying causes of this inefficiency: the redundant inversion of noisy backgrounds and the unintended inversion of spurious correlations—a phenomenon we term ``hallucination'' in model inversion. To address these limitations, we propose a novel sparse model inversion strategy, as a plug-and-play extension to speed up existing dense inversion methods with no need for modifying their original loss functions. Specifically, we selectively invert semantic foregrounds while stopping the inversion of noisy backgrounds and potential spurious correlations. Through both theoretical and empirical studies, we validate the efficacy of our approach in achieving significant inversion acceleration (up to $\times$3.79) while maintaining comparable or even enhanced downstream performance in data-free model quantization and data-free knowledge transfer. Code is available at https://github.com/Egg-Hu/SMI.

We consider a cooperative learning scenario where a collection of networked agents with individually owned classifiers dynamically update their predictions, for the same classification task, through communication or observations of each other’s predictions. Clearly if highly influential vertices use erroneous classifiers, there will be a negative effect on the accuracy of all the agents in the network. We ask the following question: how can we optimally fix the prediction of a few classifiers so as maximize the overall accuracy in the entire network. To this end we consider an aggregate and an egalitarian objective function. We show a polynomial time algorithm for optimizing the aggregate objective function, and show that optimizing the egalitarian objective function is NP-hard. Furthermore, we develop approximation algorithms for the egalitarian improvement. The performance of all of our algorithms are guaranteed by mathematical analysis and backed by experiments on synthetic and real data.

Sequential decision-making algorithms such as reinforcement learning (RL) in real-world scenarios inevitably face environments with partial observability. This paper scrutinizes the effectiveness of a popular architecture, namely Transformers, in Partially Observable Markov Decision Processes (POMDPs) and reveals its theoretical limitations. We establish that regular languages, which Transformers struggle to model, are reducible to POMDPs. This poses a significant challenge for Transformers in learning POMDP-specific inductive biases, due to their lack of inherent recurrence found in other models like RNNs. This paper casts doubt on the prevalent belief in Transformers as sequence models for RL and proposes to introduce a point-wise recurrent structure. The Deep Linear Recurrent Unit (LRU) emerges as a well-suited alternative for Partially Observable RL, with empirical results highlighting the sub-optimal performance of the Transformer and considerable strength of LRU.

What do different contrastive learning (CL) losses actually optimize for? Although multiple CL methods have demonstrated remarkable representation learning capabilities, the differences in their inner workings remain largely opaque. In this work, we analyse several CL families and prove that, under certain conditions, they admit the same minimisers when optimizing either their batch-level objectives or their expectations asymptotically. In both cases, an intimate connection with the hyperspherical energy minimisation (HEM) problem resurfaces. Drawing inspiration from this, we introduce a novel CL objective, coined Decoupled Hyperspherical Energy Loss (DHEL). DHEL simplifies the problem by decoupling the target hyperspherical energy from the alignment of positive examples while preserving the same theoretical guarantees. Going one step further, we show the same results hold for another relevant CL family, namely kernel contrastive learning (KCL), with the additional advantage of the expected loss being independent of batch size, thus identifying the minimisers in the non-asymptotic regime. Empirical results demonstrate improved downstream performance and robustness across combinations of different batch sizes and hyperparameters and reduced dimensionality collapse, on several computer vision datasets.

Monotonic Linear Interpolation (MLI) refers to the peculiar phenomenon that the error between the initial and converged model monotonically decreases along the linear interpolation, i.e., $(1-\alpha)\boldsymbol{\theta}_0 + \alpha \boldsymbol{\theta}_F$. Previous works focus on paired initial and converged points, relating MLI to the smoothness of the optimization trajectory. In this paper, we find a shocking fact that the error curves still exhibit a monotonic decrease when $\boldsymbol{\theta}_0$ is replaced with noise or even zero values, implying that the decreasing curve may be primarily related to the property of the converged model rather than the optimization trajectory. We further explore the relationship between $\alpha\boldsymbol{\theta}_F$ and $\boldsymbol{\theta}_F$ and propose scale invariance properties in various cases, including Generalized Scale Invariance (GSI), Rectified Scale Invariance (RSI), and Normalized Scale Invariance (NSI). From an inverse perspective, the MLI formula is essentially an equation that adds varying levels of noise (i.e., $(1-\alpha)\boldsymbol{\epsilon}$) to a nearly scale-invariant network (i.e., $\alpha \boldsymbol{\theta}_F$), resulting in a monotonically increasing error as the noise level rises. MLI is a special case where $\boldsymbol{\epsilon}$ is equal to $\boldsymbol{\theta}_0$.

Recent advances in knowledge graph embedding (KGE) rely on Euclidean/hyperbolic orthogonal relation transformations to model intrinsic logical patterns and topological structures. However, existing approaches are confined to rigid relational orthogonalization with restricted dimension and homogeneous geometry, leading to deficient modeling capability. In this work, we move beyond these approaches in terms of both dimension and geometry by introducing a powerful framework named GoldE, which features a universal orthogonal parameterization based on a generalized form of Householder reflection. Such parameterization can naturally achieve dimensional extension and geometric unification with theoretical guarantees, enabling our framework to simultaneously capture crucial logical patterns and inherent topological heterogeneity of knowledge graphs. Empirically, GoldE achieves state-of-the-art performance on three standard benchmarks. Codes are available at https://github.com/xxrep/GoldE.

Optimal transport (OT) and the related Wasserstein metric ($W$) are powerful and ubiquitous tools for comparing distributions. However, computing pairwise Wasserstein distances rapidly becomes intractable as cohort size grows. An attractive alternative would be to find an embedding space in which pairwise Euclidean distances map to OT distances, akin to standard multidimensional scaling (MDS). We present Wasserstein Wormhole, a transformer-based autoencoder that embeds empirical distributions into a latent space wherein Euclidean distances approximate OT distances. Extending MDS theory, we show that our objective function implies a bound on the error incurred when embedding non-Euclidean distances. Empirically, distances between Wormhole embeddings closely match Wasserstein distances, enabling linear time computation of OT distances. Along with an encoder that maps distributions to embeddings, Wasserstein Wormhole includes a decoder that maps embeddings back to distributions, allowing for operations in the embedding space to generalize to OT spaces, such as Wasserstein barycenter estimation and OT interpolation. By lending scalability and interpretability to OT approaches, Wasserstein Wormhole unlocks new avenues for data analysis in the fields of computational geometry and single-cell biology.

Reinforcement Learning from Human Feedback (RLHF) is key to aligning Large Language Models (LLMs), typically paired with the Proximal Policy Optimization (PPO) algorithm. While PPO is a powerful method designed for general reinforcement learning tasks, it is overly sophisticated for LLMs, leading to laborious hyper-parameter tuning and significant computation burdens. To make RLHF efficient, we present ReMax, which leverages 3 properties of RLHF: fast simulation, deterministic transitions, and trajectory-level rewards. These properties are not exploited in PPO, making it less suitable for RLHF. Building on the renowned REINFORCE algorithm, ReMax does not require training an additional value model as in PPO and is further enhanced with a new variance reduction technique. ReMax offers several benefits over PPO: it is simpler to implement, eliminates more than 4 hyper-parameters in PPO, reduces GPU memory usage, and shortens training time. ReMax can save about 46% GPU memory than PPO when training a 7B model and enables training on A800-80GB GPUs without the memory-saving offloading technique needed by PPO. Applying ReMax to a Mistral-7B model resulted in a 94.78% win rate on the AlpacaEval leaderboard and a 7.739 score on MT-bench, setting a new SOTA for open-source 7B models. These results show the effectiveness of ReMax while addressing the limitations of PPO in LLMs.

In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily emphasize improvement in expected performance, lacking the ability to control over the worst-case performance outcomes. To address this limitation, we introduce a novel objective function, optimizing which leads to guaranteed monotonic improvement in the lower probability bound of performance with high confidence. Building upon this groundbreaking theoretical advancement, we further introduce a practical solution called Absolute Policy Optimization (APO). Our experiments demonstrate the effectiveness of our approach across challenging continuous control benchmark tasks and extend its applicability to mastering Atari games. Our findings reveal that APO as well as its efficient variation Proximal Absolute Policy Optimization (PAPO) significantly outperforms state-of-the-art policy gradient algorithms, resulting in substantial improvements in worst-case performance, as well as expected performance.

Reinforcement learning (RL) problems where the learner attempts to infer an unobserved reward from some feedback variables have been studied in several recent papers. The setting of Interaction-Grounded Learning (IGL) is an example of such feedback-based reinforcement learning tasks where the learner optimizes the return by inferring latent binary rewards from the interaction with the environment. In the IGL setting, a relevant assumption used in the RL literature is that the feedback variable $Y$ is conditionally independent of the context-action $(X,A)$ given the latent reward $R$. In this work, we propose *Variational Information-based IGL (VI-IGL)* as an information-theoretic method to enforce the conditional independence assumption in the IGL-based RL problem. The VI-IGL framework learns a reward decoder using an information-based objective based on the conditional mutual information (MI) between the context-action $(X,A)$ and the feedback variable $Y$ observed from the environment. To estimate and optimize the information-based terms for the continuous random variables in the RL problem, VI-IGL leverages the variational representation of mutual information and results in a min-max optimization problem. Theoretical analysis shows that the optimization problem can be sample-efficiently solved. Furthermore, we extend the VI-IGL framework to general $f$-Information measures in the information theory literature, leading to the generalized $f$-VI-IGL framework to address the RL problem under the IGL condition. Finally, the empirical results on several reinforcement learning settings indicate an improved performance in comparison to the previous IGL-based RL algorithm.