论文检索

Deep Learning · Theory

Hugo Chateau-Laurent, Frederic Alexandre

Neural Episodic Control is a powerful reinforcement learning framework that employs a differentiable dictionary to store non-parametric memories. It was inspired by episodic memory on the functional level, but lacks a direct theoretical connection to the associative memory models generally used to implement such a memory. We first show that the dictionary is an instance of the recently proposed Universal Hopfield Network framework. We then introduce a continuous approximation of the dictionary readout operation in order to derive two energy functions that are Lyapunov functions of the dynamics. Finally, we empirically show that the dictionary outperforms the Max separation function, which had previously been argued to be optimal, and that performance can further be improved by replacing the Euclidean distance kernel by a Manhattan distance kernel. These results are enabled by the generalization capabilities of the dictionary, so a novel criterion is introduced to disentangle memorization from generalization when evaluating associative memory models.

Reinforcement Learning · Deep RL

Akhil Agnihotri, Rahul Jain, Deepak Ramachandran, Sahil Singla

In this paper, we present the e-COP algorithm, the first policy optimization algorithm for constrained Reinforcement Learning (RL) in episodic (finite horizon) settings. Such formulations are applicable when there are separate sets of optimization criteria and constraints on a system's behavior. We approach this problem by first establishing a policy difference lemma for the episodic setting, which provides the theoretical foundation for the algorithm. Then, we propose to combine a set of established and novel solution ideas to yield the e-COP algorithm that is easy to implement and numerically stable, and provide a theoretical guarantee on optimality under certain scaling assumptions. Through extensive empirical analysis using benchmarks in the Safety Gym suite, we show that our algorithm has similar or better performance than SoTA (non-episodic) algorithms adapted for the episodic setting. The scalability of the algorithm opens the door to its application in safety-constrained Reinforcement Learning from Human Feedback for Large Language or Diffusion Models.

Souradip Chakraborty, Soumya Suvra Ghosal, Ming Yin, Dinesh Manocha, Mengdi Wang, Amrit Singh Bedi, Furong Huang

Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billions of model parameters. A promising alternative, alignment via decoding, adjusts the response distribution directly without model updates to maximize a target reward $r$, thus providing a lightweight and adaptable framework for alignment. However, principled decoding methods rely on oracle access to an optimal Q-function ($Q^*$), which is often unavailable in practice. Hence, prior SoTA methods either approximate this $Q^*$ using $Q^{\pi_{\text{sft}}}$ (derived from the reference $\texttt{SFT}$ model) or rely on short-term rewards, resulting in sub-optimal decoding performance. In this work, we propose $\texttt{Transfer Q}^*$, which implicitly estimates the optimal value function for a target reward $r$ through a baseline model $\rho_{\texttt{BL}}$ aligned with a baseline reward $r_{\texttt{BL}}$ (which can be different from the target reward $r$). Theoretical analyses of $\texttt{Transfer Q}^*$ provide a rigorous characterization of its optimality, deriving an upper bound on the sub-optimality gap and identifying a hyperparameter to control the deviation from the pre-trained reference $\texttt{SFT}$ model based on user needs. Our approach significantly reduces the sub-optimality gap observed in prior SoTA methods and demonstrates superior empirical performance across key metrics such as coherence, diversity, and quality in extensive tests on several synthetic and real datasets.

Interpretability

Claudia Shi, Nicolas Beltran Velez, Achille Nazaret, Carolina Zheng, Adrià Garriga-Alonso, Andrew Jesson, Maggie Makar, David Blei

Large language models (LLMs) demonstrate surprising capabilities, but we do not understand how they are implemented. One hypothesis suggests that these capabilities are primarily executed by small subnetworks within the LLM, known as circuits. But how can we evaluate this hypothesis?In this paper, we formalize a set of criteria that a circuit is hypothesized to meet and develop a suite of hypothesis tests to evaluate how well circuits satisfy them. The criteria focus on the extent to which the LLM's behavior is preserved, the degree of localization of this behavior, and whether the circuit is minimal.We apply these tests to six circuits described in the research literature. We find that synthetic circuits -- circuits that are hard-coded in the model -- align with the idealized properties. Circuits discovered in Transformer models satisfy the criteria to varying degrees.To facilitate future empirical studies of circuits, we created the \textit{circuitry} package, a wrapper around the \textit{TransformerLens} library, which abstracts away lower-level manipulations of hooks and activations. The software is available at \url{https://github.com/blei-lab/circuitry}.

Kwangho Kim, Jisu Kim, Larry Wasserman, Edward Kennedy

Understanding treatment effect heterogeneity is vital for scientific and policy research. However, identifying and evaluating heterogeneous treatment effects pose significant challenges due to the typically unknown subgroup structure. Recently, a novel approach, causal k-means clustering, has emerged to assess heterogeneity of treatment effect by applying the k-means algorithm to unknown counterfactual regression functions. In this paper, we expand upon this framework by integrating hierarchical and density-based clustering algorithms. We propose plug-in estimators which are simple and readily implementable using off-the-shelf algorithms. Unlike k-means clustering, which requires the margin condition, our proposed estimators do not rely on strong structural assumptions on the outcome process. We go on to study their rate of convergence, and show that under the minimal regularity conditions, the additional cost of causal clustering is essentially the estimation error of the outcome regression functions. Our findings significantly extend the capabilities of the causal clustering framework, thereby contributing to the progression of methodologies for identifying homogeneous subgroups in treatment response, consequently facilitating more nuanced and targeted interventions. The proposed methods also open up new avenues for clustering with generic pseudo-outcomes. We explore finite sample properties via simulation, and illustrate the proposed methods in voting and employment projection datasets.

Multimodal Models

Mohammad Sadil Khan, Sankalp Sinha, Talha Uddin, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal

Prototyping complex computer-aided design (CAD) models in modern softwares can be very time-consuming. This is due to the lack of intelligent systems that can quickly generate simpler intermediate parts. We propose Text2CAD, the first AI framework for generating text-to-parametric CAD models using designer-friendly instructions for all skill levels. Furthermore, we introduce a data annotation pipeline for generating text prompts based on natural language instructions for the DeepCAD dataset using Mistral and LLaVA-NeXT. The dataset contains $\sim170$K models and $\sim660$K text annotations, from abstract CAD descriptions (e.g., _generate two concentric cylinders_) to detailed specifications (e.g., _draw two circles with center_ $(x,y)$ and _radius_ $r_{1}$, $r_{2}$, \textit{and extrude along the normal by} $d$...). Within the Text2CAD framework, we propose an end-to-end transformer-based auto-regressive network to generate parametric CAD models from input texts. We evaluate the performance of our model through a mixture of metrics, including visual quality, parametric precision, and geometrical accuracy. Our proposed framework shows great potential in AI-aided design applications. Project page is available at https://sadilkhan.github.io/text2cad-project/.

Theory · Reinforcement Learning and Planning

Zhongchang Sun, Sihong He, Fei Miao, Shaofeng Zou

This paper studies first-order policy optimization for robust average cost Markov decision processes (MDPs). Specifically, we focus on ergodic Markov chains. For robust average cost MDPs, the goal is to optimize the worst-case average cost over an uncertainty set of transition kernels. We first develop a sub-gradient of the robust average cost. Based on the sub-gradient, a robust policy mirror descent approach is further proposed. To characterize its iteration complexity, we develop a lower bound on the difference of robust average cost between two policies and further show that the robust average cost satisfies the PL-condition. We then show that with increasing step size, our robust policy mirror descent achieves a linear convergence rate in the optimality gap, and with constant step size, our algorithm converges to an $\epsilon$-optimal policy with an iteration complexity of $\mathcal{O}(1/\epsilon)$. The convergence rate of our algorithm matches with the best convergence rate of policy-based algorithms for robust MDPs. Moreover, our algorithm is the first algorithm that converges to the global optimum with general uncertainty sets for robust average cost MDPs. We provide simulation results to demonstrate the performance of our algorithm.

Fei Shen, Jinhui Tang

Diffusion models represent a promising avenue for image generation, having demonstrated competitive performance in pose-guided person image generation. However, existing methods are limited to generating target images from a source image and a target pose, overlooking two critical user scenarios: generating multiple target images with different poses simultaneously and generating target images from multi-view source images.To overcome these limitations, we propose IMAGPose, a unified conditional framework for pose-guided image generation, which incorporates three pivotal modules: a feature-level conditioning (FLC) module, an image-level conditioning (ILC) module, and a cross-view attention (CVA) module. Firstly, the FLC module combines the low-level texture feature from the VAE encoder with the high-level semantic feature from the image encoder, addressing the issue of missing detail information due to the absence of a dedicated person image feature extractor. Then, the ILC module achieves an alignment of images and poses to adapt to flexible and diverse user scenarios by injecting a variable number of source image conditions and introducing a masking strategy.Finally, the CVA module introduces decomposing global and local cross-attention, ensuring local fidelity and global consistency of the person image when multiple source image prompts. The three modules of IMAGPose work together to unify the task of person image generation under various user scenarios.Extensive experiment results demonstrate the consistency and photorealism of our proposed IMAGPose under challenging user scenarios. The code and model will be available at https://github.com/muzishen/IMAGPose.

Generative Models · Diffusion models

xiaohong chen, Canran Xiao, Yongmei liu

Federated learning has become a pivotal distributed learning paradigm, involving collaborative model updates across multiple nodes with private data. However, handling non-i.i.d. (not identically and independently distributed) data and ensuring model consistency across heterogeneous environments present significant challenges. These challenges often lead to model performance degradation and increased difficulty in achieving effective communication among participant models. In this work, we propose Confusion-Resistant Federated Learning via Consistent Diffusion (CRFed), a novel framework designed to address these issues. Our approach introduces a new diffusion-based data harmonization mechanism that includes data augmentation, noise injection, and iterative denoising to ensure consistent model updates across non-i.i.d. data distributions. This mechanism aims to reduce data distribution disparities among participating nodes, enhancing the coordination and consistency of model updates. Moreover, we design a confusion-resistant strategy leveraging an indicator function and adaptive learning rate adjustment to mitigate the adverse effects of data heterogeneity and model inconsistency. Specifically, we calculate importance sampling weights based on the optimal sampling probability, which guides the selection of clients and the sampling of their data, ensuring that model updates are robust and aligned across different nodes. Extensive experiments on benchmark datasets, including MNIST, FashionMNIST, CIFAR-10, CIFAR-100, and NIPD, demonstrate the effectiveness of CRFed in improving accuracy, convergence speed, and overall robustness in federated learning scenarios with severe data heterogeneity.

Generative Models · In Context Learning

Zhaoxuan Wu, Xiaoqiang Lin, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low

Large language models (LLMs) have shown impressive capabilities in real-world applications. The capability of *in-context learning* (ICL) allows us to adapt an LLM to downstream tasks by including input-label exemplars in the prompt without model fine-tuning. However, the quality of these exemplars in the prompt greatly impacts performance, highlighting the need for an effective automated exemplar selection method. Recent studies have explored retrieval-based approaches to select exemplars tailored to individual test queries, which can be undesirable due to extra test-time computation and an increased risk of data exposure. Moreover, existing methods fail to adequately account for the impact of exemplar ordering on the performance. On the other hand, the impact of the *instruction*, another essential component in the prompt given to the LLM, is often overlooked in existing exemplar selection methods. To address these challenges, we propose a novel method named $\texttt{EASE}$, which leverages the hidden embedding from a pre-trained language model to represent ordered sets of exemplars and uses a neural bandit algorithm to optimize the sets of exemplars *while accounting for exemplar ordering*. Our $\texttt{EASE}$ can efficiently find an ordered set of exemplars that *performs well for all test queries* from a given task, thereby eliminating test-time computation. Importantly, $\texttt{EASE}$ can be readily extended to *jointly optimize both the exemplars and the instruction*. Through extensive empirical evaluations (including novel tasks), we demonstrate the superiority of $\texttt{EASE}$ over existing methods, and reveal practical insights about the impact of exemplar selection on ICL, which may be of independent interest. Our code is available at https://github.com/ZhaoxuanWu/EASE-Prompt-Optimization.

Generative Models · Diffusion models

Junsheng Zhou, Weiqi Zhang, Yu-Shen Liu

3D Gaussian Splatting (3DGS) has shown convincing performance in rendering speed and fidelity, yet the generation of Gaussian Splatting remains a challenge due to its discreteness and unstructured nature. In this work, we propose DiffGS, a general Gaussian generator based on latent diffusion models. DiffGS is a powerful and efficient 3D generative model which is capable of generating Gaussian primitives at arbitrary numbers for high-fidelity rendering with rasterization. The key insight is to represent Gaussian Splatting in a disentangled manner via three novel functions to model Gaussian probabilities, colors and transforms. Through the novel disentanglement of 3DGS, we represent the discrete and unstructured 3DGS with continuous Gaussian Splatting functions, where we then train a latent diffusion model with the target of generating these Gaussian Splatting functions both unconditionally and conditionally. Meanwhile, we introduce a discretization algorithm to extract Gaussians at arbitrary numbers from the generated functions via octree-guided sampling and optimization. We explore DiffGS for various tasks, including unconditional generation, conditional generation from text, image, and partial 3DGS, as well as Point-to-Gaussian generation. We believe that DiffGS provides a new direction for flexibly modeling and generating Gaussian Splatting. Project page: https://junshengzhou.github.io/DiffGS.

Tianyu Chen, Zhendong Wang, Mingyuan Zhou

Offline reinforcement learning (RL) leverages pre-collected datasets to train optimal policies. Diffusion Q-Learning (DQL), introducing diffusion models as a powerful and expressive policy class, significantly boosts the performance of offline RL. However, its reliance on iterative denoising sampling to generate actions slows down both training and inference. While several recent attempts have tried to accelerate diffusion-QL, the improvement in training and/or inference speed often results in degraded performance. In this paper, we introduce a dual policy approach, Diffusion Trusted Q-Learning (DTQL), which comprises a diffusion policy for pure behavior cloning and a practical one-step policy. We bridge the two polices by a newly introduced diffusion trust region loss. The diffusion policy maintains expressiveness, while the trust region loss directs the one-step policy to explore freely and seek modes within the region defined by the diffusion policy. DTQL eliminates the need for iterative denoising sampling during both training and inference, making it remarkably computationally efficient. We evaluate its effectiveness and algorithmic characteristics against popular Kullback-Leibler (KL) based distillation methods in 2D bandit scenarios and gym tasks. We then show that DTQL could not only outperform other methods on the majority of the D4RL benchmark tasks but also demonstrate efficiency in training and inference speeds. The PyTorch implementation is available at https://github.com/TianyuCodings/Diffusion_Trusted_Q_Learning.

Deep Learning · Algorithms

Wenlin Chen, Hong Ge

We introduce a novel approach for analyzing the training dynamics of ReLU networks by examining the characteristic activation boundaries of individual ReLU neurons. Our proposed analysis reveals a critical instability in common neural network parameterizations and normalizations during stochastic optimization, which impedes fast convergence and hurts generalization performance. Addressing this, we propose Geometric Parameterization (GmP), a novel neural network parameterization technique that effectively separates the radial and angular components of weights in the hyperspherical coordinate system. We show theoretically that GmP resolves the aforementioned instability issue. We report empirical results on various models and benchmarks to verify GmP's advantages of optimization stability, convergence speed and generalization performance.

Learning Theory

Xiyuan Li, Weiwei Liu

The Stackelberg prediction game (SPG) is a popular model for characterizing strategic interactions between a learner and an adversarial data provider. Although optimization problems in SPGs are often NP-hard, a notable special case involving the least squares loss (SPG-LS) has gained significant research attention recently, (Bishop et al. 2020; Wang et al. 2021; Wang et al. 2022). The latest state-of-the-art method for solving the SPG-LS problem is the spherically constrained least squares reformulation (SCLS) method proposed in the work of Wang et al. (2022). However, the lack of theoretical analysis on the error of the SCLS method limits its large-scale applications. In this paper, we investigate the estimation error between the learner obtained by the SCLS method and the actual learner. Specifically, we reframe the estimation error of the SCLS method as a Primary Optimization ($\textbf{PO}$) problem and utilize the Convex Gaussian min-max theorem (CGMT) to transform the $\textbf{PO}$ problem into an Auxiliary Optimization ($\textbf{AO}$) problem. Subsequently, we provide a theoretical error analysis for the SCLS method based on this simplified $\textbf{AO}$ problem. This analysis not only strengthens the theoretical framework of the SCLS method but also confirms the reliability of the learner produced by it. We further conduct experiments to validate our theorems, and the results are in excellent agreement with our theoretical predictions.

Xin Zou, Zhengyu Zhou, Jingyuan Xu, Weiwei Liu

AdaBoost is a well-known algorithm in boosting. Schapire and Singer propose, an extension of AdaBoost, named AdaBoost.MH, for multi-class classification problems. Kégl shows empirically that AdaBoost.MH works better when the classical one-against-all base classifiers are replaced by factorized base classifiers containing a binary classifier and a vote (or code) vector. However, the factorization makes it much more difficult to provide a convergence result for the factorized version of AdaBoost.MH. Then, Kégl raises an open problem in COLT 2014 to look for a convergence result for the factorized AdaBoost.MH. In this work, we resolve this open problem by presenting a convergence result for AdaBoost.MH with factorized multi-class classifiers.

Graph Neural Networks

Zhibiao Wang, Xiao Wang, Haoyue Deng, Nian Liu, Shirui Pan, Chunming Hu

Graph self-supervised learning, as a powerful pre-training paradigm for Graph Neural Networks (GNNs) without labels, has received considerable attention. We have witnessed the success of graph self-supervised learning on pre-training the parameters of GNNs, leading many not to doubt that whether the learned GNNs parameters are all useful. In this paper, by presenting the experimental evidence and analysis, we surprisingly discover that the graph self-supervised learning models are highly redundant at both of neuron and layer levels, e.g., even randomly removing 51.6\% of parameters, the performance of graph self-supervised learning models still retains at least 96.2\%. This discovery implies that the parameters of graph self-supervised models can be largely reduced, making simultaneously fine-tuning both graph self-supervised learning models and prediction layers more feasible. Therefore, we further design a novel graph pre-training and fine-tuning paradigm called SLImming DE-correlation Fine-tuning (SLIDE). The effectiveness of SLIDE is verified through extensive experiments on various benchmarks, and the performance can be even improved with fewer parameters of models in most cases. For example, in comparison with full fine-tuning GraphMAE on Amazon-Computers dataset, even randomly reducing 40\% of parameters, we can still achieve the improvement of 0.24\% and 0.27\% for Micro-F1 and Macro-F1 scores respectively.

Shuhao Chen, Weisen Jiang, Baijiong Lin, James Kwok, Yu Zhang

Recent works show that assembling multiple off-the-shelf large language models (LLMs) can harness their complementary abilities. To achieve this, routing is a promising method, which learns a router to select the most suitable LLM for each query. However, existing routing models are ineffective when multiple LLMs perform well for a query. To address this problem, in this paper, we propose a method called query-based Router by Dual Contrastive learning (RouterDC). The RouterDC model, which consists of an encoder and LLM embeddings, is trained by two proposed contrastive losses (sample-LLM and sample-sample losses). Experimental results show that RouterDC is effective in assembling LLMs and largely outperforms individual top-performing LLMs as well as existing routing methods on both in-distribution (+2.76\%) and out-of-distribution (+1.90\%) tasks. The source code is available at https://github.com/shuhao02/RouterDC.

Reinforcement Learning · Deep RL

HYUNSEUNG KIM, BYUNG KUN LEE, Hojoon Lee, Dongyoon Hwang, Donghu Kim, Jaegul Choo

Unsupervised skill discovery is a learning paradigm that aims to acquire diverse behaviors without explicit rewards. However, it faces challenges in learning complex behaviors and often leads to learning unsafe or undesirable behaviors. For instance, in various continuous control tasks, current unsupervised skill discovery methods succeed in learning basic locomotions like standing but struggle with learning more complex movements such as walking and running. Moreover, they may acquire unsafe behaviors like tripping and rolling or navigate to undesirable locations such as pitfalls or hazardous areas. In response, we present **DoDont** (Do’s and Dont’s), an instruction-based skill discovery algorithm composed of two stages. First, in instruction learning stage, DoDont leverages action-free instruction videos to train an instruction network to distinguish desirable transitions from undesirable ones. Then, in the skill learning stage, the instruction network adjusts the reward function of the skill discovery algorithm to weight the desired behaviors. Specifically, we integrate the instruction network into a distance-maximizing skill discovery algorithm, where the instruction network serves as the distance function. Empirically, with less than 8 instruction videos, DoDont effectively learns desirable behaviors and avoids undesirable ones across complex continuous control tasks. Code and videos are available at https://mynsng.github.io/dodont/

Graph Neural Networks

Qixun Wang, Yifei Wang, Yisen Wang, Xianghua Ying

Enhancing node-level Out-Of-Distribution (OOD) generalization on graphs remains a crucial area. In this paper, we develop a Structural Causal Model (SCM) to theoretically dissect the performance of two prominent invariant learning methods--Invariant Risk Minimization (IRM) and Variance-Risk Extrapolation (VREx)--in node-level OOD settings. Our analysis reveals a critical limitation: these methods may struggle to identify invariant features due to the complexities introduced by the message-passing mechanism, which can obscure causal features within a range of neighboring samples. To address this, we propose Cross-environment Intra-class Alignment (CIA), which explicitly eliminates spurious features by aligning representations within the same class, bypassing the need for explicit knowledge of underlying causal patterns. To adapt CIA to node-level OOD scenarios where environment labels are hard to obtain, we further propose CIA-LRA (Localized Reweighting Alignment) that leverages the distribution of neighboring labels to selectively align node representations, effectively distinguishing and preserving invariant features while removing spurious ones, all without relying on environment labels. We theoretically prove CIA-LRA's effectiveness by deriving an OOD generalization error bound based on PAC-Bayesian analysis. Experiments on graph OOD benchmarks validate the superiority of CIA and CIA-LRA, marking a significant advancement in node-level OOD generalization.

Computer Vision · Video Understanding

Khoa Vo, Thinh Phan, Kashu Yamazaki, Minh Tran, Ngan Le

Current video-language models (VLMs) rely extensively on instance-level alignment between video and language modalities, which presents two major limitations: (1) visual reasoning disobeys the natural perception that humans do in first-person perspective, leading to a lack of reasoning interpretation; and (2) learning is limited in capturing inherent fine-grained relationships between two modalities.In this paper, we take an inspiration from human perception and explore a compositional approach for egocentric video representation. We introduce HENASY (Hierarchical ENtities ASsemblY), which includes a spatiotemporal token grouping mechanism to explicitly assemble dynamically evolving scene entities through time and model their relationship for video representation. By leveraging compositional structure understanding, HENASY possesses strong interpretability via visual grounding with free-form text queries. We further explore a suite of multi-grained contrastive losses to facilitate entity-centric understandings. This comprises three alignment types: video-narration, noun-entity, verb-entities alignments.Our method demonstrates strong interpretability in both quantitative and qualitative experiments; while maintaining competitive performances on five downstream tasks via zero-shot transfer or as video/text representation, including video/text retrieval, action recognition, multi-choice query, natural language query, and moments query.Project page: https://uark-aicv.github.io/HENASY