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.

UAI 2026

Verbalizing LLM’s Higher-order Uncertainty via Imprecise Probabilities

Anita Yang, Krikamol Muandet, Michele Caprio, Siu Lun Chau, Masaki Adachi

Despite the growing demand for eliciting uncertainty from large language models (LLMs), empirical evidence suggests that LLM behavior is not always adequately captured by the elicitation techniques developed under the classical probabilistic uncertainty framework. This mismatch leads to systematic failure modes, particularly in settings that involve ambiguous question-answering, in-context learning, and self-reflection. To address this, we propose novel prompt-based uncertainty elicitation techniques grounded in *imprecise probabilities*, a principled framework for representing and eliciting higher-order uncertainty. Here, first-order uncertainty captures uncertainty over possible responses to a prompt, while second-order uncertainty (uncertainty about uncertainty) quantifies indeterminacy in the underlying probability model itself. We introduce general-purpose prompting and post-processing procedures to directly elicit and quantify both orders of uncertainty, and demonstrate their effectiveness across diverse settings. Our approach enables more faithful uncertainty reporting from LLMs, improving credibility and supporting downstream decision-making.

UAI 2026

ReVAD: From Imitation to Reasoning in Vectorized Autonomous Driving via Latent Space Search

Zhao Yang, Chengkang Duan, Weiyi Hu, Haoran Hu, Hua Cui, Qingshuang Sun

Vectorized end-to-end (E2E) autonomous driving models predominantly rely on reactive imitation learning. By failing to model underlying environmental dynamics, these agents lack counterfactual reasoning capabilities and struggle with uncertainty in out-of-distribution (OOD) scenarios. To bridge the gap between reactive imitation and deliberative decision-making, we introduce Reasoning-enhanced VAD (ReVAD), empowering agents with a “System 2” cognitive framework via Latent Space Search. Unlike computationally expensive pixel-level world models, ReVAD integrates a probabilistic Token Dynamics Model with Latent Monte Carlo Tree Search to perform efficient lookahead planning entirely within a sparse semantic token space. By simulating future states to evaluate risk and utilizing imitation policies solely as search priors, ReVAD effectively mitigates the distribution shift inherent in pure imitation learning, demonstrating significantly improved robustness and safety in high-uncertainty environments.

UAI 2026

One-Shot Federated Learning based on Random Feature Extractor

Luyuan Yang, Shayan Shafaei, Yiming Liu, Naeem Shahabi Sani, Yu Cai, Jun Huan, Chao Lan

The transition from multi-rounds federated learning to one-shot federated learning (OFL) markedly alleviates communication burden and represents a major step toward realistic deployment. Most existing OFL approaches require clients to perform local training, imposing a substantial computational burden on client side, while others rely on pre-trained models. In this paper, we propose a novel one-shot federated learning framework based on random feature extractor (FedRFE). Unlike existing approaches, it does not require any local model training or pre-trained model, featuring superior resource efficiency. Through comprehensive experiments, we show FedRFE achieves competitive performance while being robust in challenging scenarios including data heterogeneity and client scalability. Our code is available at<https://github.com/luyuanxyang/FedRFE>

UAI 2026

Robust Decision-Focused Learning via Worst-Case Regret Minimization

Shoki Yamao, Ken Kobayashi, Ryo Matsui, Shota Nagai, Naoki Nishimura, Kazuhide Nakata

In optimization-based decision-making, when the objective coefficient vector is unknown, a common approach is to predict it from covariates using a machine learning model and solve the downstream optimization problem. However, improving predictive accuracy does not necessarily lead to better decisions. This has motivated Decision-Focused Learning (DFL), which trains predictive models to minimize decision loss measured by regret. Despite recent progress, existing DFL methods do not sufficiently address two sources of uncertainty: (i) observation errors in the measured coefficients, and (ii) distribution shift in the coefficient vector at deployment due to environmental changes. These uncertainties can degrade solution quality. In this paper, we propose two robust regret losses to address these uncertainties. For uncertainty (i), we introduce an uncertainty set around the observed coefficient vector that captures measurement errors and define the loss as the worst-case regret over this set. For uncertainty (ii), we construct a Wasserstein ambiguity set around the conditional empirical distribution and define the loss using the worst-case distribution within the set. We enable efficient training via Danskin-based subgradients. Experiments demonstrate that our method reduces regret and yields more stable solutions than existing robust DFL approaches.

UAI 2026

Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization

Ryusei Yamada, Naoki Sato, Hideaki Iiduka

Stochastic Gradient Descent (SGD) is a cornerstone of modern optimization. While its performance under heavy-tailed noise is often addressed through specialized modifications such as gradient clipping or normalization, we investigate a more fundamental question: how does vanilla SGD, particularly with momentum, perform in the presence of heavy-tailed noise? In this paper, we refine existing convergence results for vanilla SGD and, more importantly, provide the first comprehensive convergence analysis of vanilla SGD with momentum for strongly convex, convex, and nonconvex objectives, without employing any gradient control mechanisms. Our results demonstrate that the obtained convergence rates are inferior to the optimal rates achieved by clipped or normalized variants of SGD, thereby revealing inherent limitations of vanilla methods under heavy-tailed noise. The theoretical findings are supported by experiments on synthetic functions.

UAI 2026

Implicit Variational Rejection Sampling

Jian Xu, Shigui Li, Wei Chen, Jiacheng Li, Zhiqi Lin, Delu Zeng, Xinghao Ding, John Paisley, Qibin Zhao

Variational Inference (VI) is a fundamental inference technique in Bayesian machine learning for approximating complex posterior distributions. Traditional VI often relies on the mean-field factorization, which can inadequately capture true posterior complexity. Recent advancements have leveraged neural networks to model implicit distributions, offering increased flexibility. However, the practical constraints of neural network architectures still produces inaccuracies. In this paper, we propose a method called Implicit Variational Rejection Sampling (IVRS), which integrates implicit distributions with rejection sampling to improve the posterior approximation. Our method uses neural networks to construct implicit proposal distributions, and rejection sampling with a discriminator network that estimates the density ratio between the implicit proposal and the true posterior for refining the approximation. Towards this end, we introduce the Implicit Resampling Evidence Lower Bound (IR-ELBO) as a metric to characterize the resampled distribution’s quality and derive a tighter variational lower bound. Experimental results demonstrate that our method outperforms traditional variational inference techniques.

UAI 2026

Efficient Q-Learning and Actor–Critic Methods for Robust Average-Reward Reinforcement Learning.

Yang Xu, Swetha Ganesh, Vaneet Aggarwal

We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs). We present non-asymptotic convergence analyses of Q-learning and actor–critic algorithms for robust average-reward MDPs under contamination, total-variation distance, and Wasserstein uncertainty sets. A key ingredient of our analysis is showing that the optimal robust Bellman operator is a strict contraction with respect to a carefully designed semi-norm. This property enables a stochastic approximation update that learns the optimal robust Q-function using 𝒪̃(ϵ^-2) samples. We also establish robust TD convergence bounds whose constants are uniform over all stationary policies, yielding an efficient data-driven routine for robust critic estimation. Building on this, we introduce an actor–critic algorithm that learns an ϵ-optimal robust policy within 𝒪̃(ϵ^-2) samples. We provide numerical simulations to illustrate the qualitative behavior of the proposed algorithms. Our results contribute to the theoretical foundations of robust planning under model misspecification, and to model-free approaches for building robust long-run policies directly from simulation data.

UAI 2026

Kronecker-Structured Nonparametric Spatiotemporal Point Processes

Zhitong Xu, Qiwei Yuan, Yinghao Chen, Yan Sun, Bin Shen, Shandian Zhe

Events in spatiotemporal domains arise in numerous real-world applications, where uncovering event relationships and enabling accurate prediction are central challenges. Classical Poisson and Hawkes processes rely on restrictive parametric assumptions that limit their ability to capture complex interaction patterns, while recent neural point process models increase representational capacity but integrate event information in a black-box manner, hindering interpretable relationship discovery. To address these limitations, we propose a Kronecker-Structured Nonparametric Spatiotemporal Point Process (KSTPP) that enables transparent event-wise relationship discovery while retaining high modeling flexibility. We model the background intensity with a spatial Gaussian process (GP) and the influence kernel as a spatiotemporal GP, allowing rich interaction patterns including excitation, inhibition, neutrality, and time-varying effects. To enable scalable training and prediction, we adopt separable product kernels and represent the GPs on structured grids, inducing Kronecker-structured covariance matrices. Exploiting Kronecker algebra substantially reduces computational cost and allows the model to scale to large event collections. In addition, we develop a tensor-product Gauss-Legendre quadrature scheme to efficiently evaluate intractable likelihood integrals. Extensive experiments demonstrate the effectiveness of our framework.

UAI 2026

How Learning Dynamics Drive Adversarially Robust Generalization?

Yuelin Xu, Xiao Zhang

Despite being widely adopted as a canonical framework for learning robust models, adversarial training suffers from robust overfitting. Existing empirical and theoretical explorations fail to provide a satisfactory mechanistic interpretation of the phenomenon. By modeling adversarial training with momentum SGD as a discrete-time dynamical system, we propose a PAC-Bayesian analytical framework that proves time-resolved robust generalization bounds. Specifically, our framework tracks the closed-form evolution of the posterior mean and covariance under both stationary and non-stationary transient regimes, connecting the model’s robust generalization performance to learning rate, local loss geometry, and mini-batch stochastic gradients. By estimating the key quantities associated with the bound, we illustrate the underlying mechanism of robust overfitting. Our framework also shows how adversarial weight perturbation reduces robust generalization gaps by suppressing dominant loss-curvature modes, while suggesting that excessive penalization can be sub-optimal for optimization.

UAI 2026

Improving online FDR procedures via online analogs of e-closure and compound e-values

Ziyu Xu, Lasse Fischer, Aaditya Ramdas

In many scientific applications, hypotheses are generated and tested continuously in a stream. We develop a framework for improving online multiple testing procedures with false discovery rate (FDR) control under arbitrary dependence. Our approach is two-fold: we construct methods via the online e-closure principle, as well as a novel formulation in online compound e-values constructed via donations. This yields strict power improvements over state-of-the-art e-value and p-value procedures while retaining FDR control. We further derive algorithms that compute the rejection decision at time t in O(log t) time, and we demonstrate improved empirical performance on synthetic and real data.

UAI 2026

ARGUS: Argumentation-Based Minimal-Change Repair for Verifiable LLM Self-Explanations

Yifan Xiao, Shijie Li

When large language models produce natural-language rationales, those explanations are frequently unfaithful to the model’s actual reasoning—and no existing framework provides a principled way to repair them when new evidence arrives. We introduce ARGUS, a framework that structures LLM self-explanations as Dung-style abstract argumentation frameworks and verifies them under grounded and preferred semantics. When new or uncertain evidence renders an explanation inconsistent, ARGUS computes a minimum-cost set of edit operations that restores the desired acceptability status of the target argument. The repair operator satisfies adapted AGM revision postulates and is bidirectionally characterized by them (Representation Theorem): the decision problem is in P under grounded semantics, NP-complete under preferred and stable semantics, and Σ_2^P-complete under skeptical stable semantics. A k-neighborhood approximation and an answer set programming (ASP) encoding ensure scalability to practical framework sizes. We validate the framework on HotpotQA and FEVER, where ARGUS achieves relative improvements of 10.3

UAI 2026

Federated Combinatorial Causal Bandits with Heterogeneous Causal Influences

Zheshun Wu, Wei Chen, Zenglin Xu, Fang Kong

We explore the problem of federated combinatorial causal bandits (FedCCB), where multiple agents collaboratively select variables for intervention and gather feedback. The primary objective of FedCCB is to identify optimal interventions for each agent while minimizing the total cumulative regret associated with the target nodes. A key challenge in FedCCB stems from the inherent heterogeneity of local causal models, which often exhibit diverse causal influences. To address this challenge, we propose a novel Federated Subset-Clustered Bandit (FedSCuB) method. This method groups agents to tackle heterogeneity based on the similarity of their causal relationships with specified subsets of variables. FedSCuB incorporates an intervention-based exploration strategy to collect partial observations necessary for clustering, as well as an alternating minimization method to facilitate collaboration among agents within the same cluster. Theoretical analysis demonstrates that the proposed FedSCuB method achieves sub-linear regret and offers a better regret bound compared to baseline methods. Empirical evaluations on synthetic tasks further confirm the effectiveness and superiority of our method.

UAI 2026

DRL-ORA: Distributional Reinforcement Learning with Online Epistemic Risk Adaptation

Yupeng Wu, Wenyun Li, Wenjie Huang, Chin Pang Ho

One of the main challenges in reinforcement learning (RL) is that the agent has to make decisions that would influence the future performance without having complete knowledge of the environment. Dynamically adjusting the level of epistemic risk during the learning process can help to achieve reliable policies in safety-critical settings with better efficiency. In this work, we propose a new framework, Distributional RL with Online Epistemic Risk Adaptation (DRL-ORA). This framework quantifies both epistemic and implicit aleatory uncertainties in a unified manner and dynamically adjusts the epistemic risk levels by solving a total variation minimization problem online. The framework generalizes the existing variants of risk adaptation approaches with better explainability and flexibility. The selection of risk levels is performed efficiently via a Follow-The-Leader-type algorithm. We show that DRL-ORA outperforms existing methods that rely on fixed risk levels or manually designed risk level adaptation in multiple classes of tasks.

UAI 2026

Concept Sketching for Description Logics

Jinghan Wu, Chang Lu, Renate Schmidt, Yizheng Zhao

Domain experts often know *part* of a target description logic (DL) concept (a conjunction involving an existential restriction here, a structural pattern there), yet every existing concept learner ignores this knowledge and searches from scratch. We introduce *concept sketching* for the DL 𝒜ℒ𝒞: the expert supplies a partial formula with typed holes (unknown subconcepts, unary or binary constructors), and any suitable back-end learner completes it from labeled examples. This *sketch fitting* problem turns out to have a sharp complexity landscape governed by a single dividing line: the signature size |Σ|. The problem is NP-complete even for a single hole; with |Σ| as parameter it becomes fixed-parameter tractable; but without |Σ| it is W[2]-hard, except for Type-2-only sketches which remain tractable. This dichotomy parallels recent results in first-order and decision tree learning. On the statistical side, we prove that each hole type contributes independently to PAC sample complexity, with a matching lower bound, so that a sketch capturing even part of the target structure requires provably fewer examples than unrestricted bounded fitting. Experiments on five standard DL benchmarks with two fundamentally different back-ends (SAT-based fitting and evolutionary concept learning) confirm improved accuracy, sample efficiency, and solver speed, demonstrating that sketching benefits are learner-agnostic.

UAI 2026

On the Convergence of Self-Improving Online LLM Alignment

Xudong Wu, Pangpang Liu, Vaneet Aggarwal, Jiayu Chen

The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the problem to an efficient, single-level method. Empirically, SAIL has demonstrated strong performance on this task. However, a formal analysis of its convergence properties has been lacking. We identify a key theoretical challenge: the standard SAIL objective function is not guaranteed to be strongly concave due to unfavorable properties of its Hessian. To address this limitation, we propose a regularized objective, SAIL-RevKL, which incorporates a reverse Kullback-Leibler (KL) divergence penalty to improve the optimization landscape. Our central theoretical contribution is to prove that this regularized objective satisfies the Polyak-Lojasiewicz (PL) condition within a bounded parameter space. We establish global convergence guarantees, achieving a near-linear sample complexity. We further validate the effectiveness and stability of SAIL-RevKL through empirical evaluations, demonstrating that it outperforms the vanilla SAIL on both MuJoCo benchmarks and LLM alignment tasks.

UAI 2026

Learning Representations from Perturbation: A Novel Matrix-View Weighting Framework for Naive Bayes

Siyao Wu, Huan Zhang, Kexin Meng, Zhipeng Ding, Pei Lv

Numerous attribute weighting methods have recently been proposed to alleviate the attribute conditional independence assumption in naive Bayes. Among them, multi-view attribute weighting framework has achieved state-of-the-art performance by constructing additional latent views beyond the raw attribute view, thereby capturing more comprehensive data characteristics. However, these latent views are usually derived from base classifiers trained on a fixed input distribution, which greatly limits the diversity of generated attributes. Additionally, in most cases, the latent views consist solely of hard labels, disregarding the predicted posterior probability of the base classifiers, resulting in incomplete utilization of discriminative evidence. To address these issues, we propose a novel framework called Perturbation-driven Matrix-view Weighted Naive Bayes (PMWNB). In PMWNB, diverse input perturbations are first applied to the raw attribute view to generate multiple base views. Subsequently, each base view independently trains multiple heterogeneous base classifiers, whose hard label and soft probability outputs are jointly leveraged to construct four latent views. Finally, class-specific attribute value weights in each view are respectively optimized by minimizing the negative conditional log-likelihood. Extensive experiments conducted on a collection of 59 benchmark datasets demonstrate the superiority of PMWNB. The source code and datasets are available at https://github.com/zhanghuan1994/PMWNB.

UAI 2026

An NTK Theory Approach to UCB Estimation in Semi-gradient TD Learning

Yijun Wu, Pascal R. van der Vaart, Moritz Akiya Zanger, Matthijs T. J. Spaan

Efficient exploration is a central challenge in reinforcement learning (RL), especially under sparse rewards, large state-action spaces, or adversarial environment dynamics. A principled approach to exploration is to choose actions that maximize the upper bound return. Under certain conditions, this can be formulated in the Bayesian framework as exploration based on the posterior variance. In practice, the predictive variance of a neural network is often used as a surrogate for the posterior variance by techniques such as ensembles, randomized priors, and random network distillation. However, for wide neural networks, neural tangent kernel (NTK) theory proves there is a discrepancy between the predictive variance of a wide neural network trained by gradient descent and its posterior variance. This is a known issue in supervised learning and there exist methods to reconcile this discrepancy. In this work, we show that, in contrast to the supervised setting, reconciliation is not possible for semi-gradient temporal difference (TD) learning, which is a commonly used algorithm in deep RL. Instead, we derive the upper confidence bound (UCB) of the value function in semi-gradient TD learning directly and show that this UCB can be estimated by a neural network. To aid our analysis, we extend NTK theory to regularized semi-gradient TD learning.

UAI 2026

Building a Bridge Between the Shapley Value, Prime Implicants and Counterfactual Explanations: a Theoretical Analysis

Hénoïk Willot

Since the introduction of SHAP, many methods adapted the idea of using the Shapley value formula as a way to measure the importance of a feature in the decision of a model. However, computing this value theoretically imply to relearn the model with and without the feature for all subsets of features. To avoid this, the methods rely on sampling to compute an expectation to measure a mean impact of a feature. In this paper we investigate theoretically if we could, and under which conditions, build and use a textbook cooperative game with the help of other explanation techniques, Prime Implicants and Counterfactual explanations, for computing Shapley values for interpretability. We propose detailed and iterative analysis of the number of remaining explanations during the enumeration of the explanations, alongside the computation of the Shapley value and its upper and lower bounds.

UAI 2026

Simplex-to-Euclidean Bijection for Conjugate and Calibrated Multiclass Gaussian Process Classification

Bernardo Williams, Harsha Vardhan Tetali, Arto Klami, Marcelo Hartmann

We propose a conjugate and calibrated Gaussian process (GP) model for multi-class classification by exploiting the geometry of the probability simplex. Our approach uses Aitchison geometry to map simplex-valued class probabilities to an unconstrained Euclidean representation, turning classification into a GP regression problem with fewer latent dimensions than standard multi-class GP classifiers. This yields conjugate inference and reliable predictive probabilities without relying on distributional approximations in the model construction. The method is compatible with standard sparse GP regression techniques, enabling scalable inference on larger datasets. Empirical results show well-calibrated and competitive performance across synthetic and real-world datasets.

UAI 2026

Single-Network Asymptotics for Causal Inference with Partial Network Data

Steven Wilkins-Reeves, Shane Lubold, Arun Chandrasekhar, Tyler McCormick

Randomized experiments are a staple in academic research, policy, and industry. Interference, when the outcome of one unit depends on the treatment status of other units, can cause bias in estimates of the treatment effect. Statistical corrections rely on knowing the underlying network of transmission pathways. Often, though, it is only possible to partially observe the network (e.g., through node subsamples, egocentric designs, respondent-driven sampling, or aggregated relational data). We develop a single-network asymptotic framework for inference about treatment effects in this regime. Starting from a structural causal model and exposure mapping, we assume a flexible class of generative network models consistent with the partial measurements and construct feasible proxy exposures by averaging over plausible completions of the network. We then study moment-based estimators for response parameters and treatment effects under dependence, and give conditions for consistency and asymptotic normality together with an explicit rate requirement ensuring that network-estimation error is first-order negligible. Simulations and an empirical replication illustrate how the theory maps to finite-sample workflows for interference with partial network data.

Keep browsing

More papers from top AI conferences

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