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

Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions

Mame Diarra Toure, David A. Stephens

In safety-critical classification, the cost of failure is often asymmetric. Yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), which cannot distinguish whether a model’s ignorance involves a benign or safety-critical class. We decompose MI into a per-class vector 𝒞_k(x)=σ_k^2/(2μ_k), with μ_k = 𝔼[p_k] and σ_k^2 = Var[p_k] across posterior samples. The decomposition follows from a second-order Taylor expansion of the entropy; the 1/μ_k weighting corrects boundary suppression and makes 𝒞_k comparable across rare and common classes. By construction ∑_k 𝒞_k ≈MI, and a companion skewness diagnostic flags inputs where the approximation degrades. After characterising the axiomatic properties of 𝒞_k, we validate it on three tasks: (i) selective prediction for diabetic retinopathy, where critical-class 𝒞_k reduces selective risk by 34.7

UAI 2026

Benign Overfitting with Quantum Kernels

Joachim Tomasi, Sandrine Anthoine, Hachem Kadri

Kernel methods compare inputs through feature maps. Quantum kernels follow the same principle: input data are encoded into quantum states, which define quantum feature representations in Hilbert spaces. Kernel values are then obtained by estimating inner products between these states using suitable quantum circuit measurements. As a result, quantum kernels may be intractable to compute classically while remaining efficiently computable on quantum hardware, potentially leading to a quantum advantage. However, designing effective quantum kernels remains a major challenge. Many quantum kernels, such as the fidelity kernel, suffer from exponential concentration. This results in near-identity kernel matrices that fail to capture meaningful data correlations and lead to overfitting and poor generalization. In this paper, we propose a novel strategy for constructing quantum kernels that achieve good generalization performance, drawing inspiration from benign overfitting in classical machine learning. We introduce the concept of Local-Global quantum kernels, which combine two components: a local quantum kernel based on measurements of small subsystems, and a global quantum kernel derived from full-system measurements. To support the effectiveness of the proposed construction, we show theoretically and empirically that Local-Global quantum kernels exhibit benign overfitting.

UAI 2026

On Pairwise Quantile Regression - Statistical Guarantees and Applications

Romain Therezien, Stephan CLEMENCON, Fantin Girard, Hamza El-Abdouni

Quantile regression provides a powerful tool for summarizing the conditional distribution of a real-valued random variable (r.v.) of interest Y as a function of covariates Z in cases where it shows a large dispersion with high probability, going beyond the situation where standard least square regression is informative/predictive. This article aims to extend this methodology to the pairwise setting, where the variable to be explained is a similarity score between two independent observations (e.g., pixelated ID photos used as input to biometric systems), and the explanatory variables consist of the pair of covariates attached to these observations, such as age or hair color. We establish theoretical guarantees for solutions of this statistical learning problem, considered here as empirical minimizers of a pairwise version of the pinball loss. Leveraging sharp concentration results for U-processes, we prove generalization bounds and identify mild conditions under which fast learning rates can be achieved. Confirming the probabilistic analysis, experiments based on simulation data also provide solid empirical evidence of the validity of the methodology promoted here for pairwise quantile regression. Finally, its usefulness from an application perspective is demonstrated by a detailed study aimed at analyzing errors in similarity scoring for facial recognition.

UAI 2026

EVIA: Entropic Variational Inference Auto-encoding

Yunfei Teng, Zhichao Chen, Xinyu Chen, Lulu Tang, Sixin Zhang, Zhouchen Lin

We present Entropic Variational Inference Auto-encoding (EVIA), a novel framework that extends classical variational approaches—including WAEs and AAEs, by incorporating entropy regularization. This regularization yields an entropic objective characterized by a closed-form Gibbs posterior, established via the Donsker–Varadhan representation. Consequently, this formulation facilitates efficient sampling strategy, allowing the model to perform high-fidelity autoencoding while jointly ensuring accurate distributional alignment. Empirical results demonstrate EVIA’s strong, consistent performance across diverse generative modeling tasks, including posterior estimation, variational inference, and image inpainting.

UAI 2026

Positive-Unlabeled Regression: learning from partially labeled quantitative outcomes

Paweł Teisseyre, Jan Mielniczuk

We study a novel machine learning problem: Positive-Unlabeled Regression (PUR), which extends the classical Positive-Unlabeled (PU) learning framework to regression setting with a non-negative, discrete target variable. This setting arises naturally in applications where only some positive quantitative outcomes are reported, while the absence of a label may either indicate a true zero outcome or an unreported positive value. Applications include predicting the number of diseases a patient may have, the number of complications following an illness, or the advancement stage of a disease. We formalize the PUR problem and highlight the limitations of naive approaches that either use reported target variable or discard unlabeled data. To account for the inherent bias in such strategies, we propose two principled methods. The first is based on calibration of regression estimates using posterior probabilities from classical PU learning. The second builds on an empirical risk minimization framework, restating the target risk as a weighted function dependent on the instance-specific propensity score. We demonstrate both theoretically and empirically that the proposed approaches yield improved performance over standard baselines.

UAI 2026

Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise

Naoto Tani, Futoshi Futami

We study linear contextual bandits under adversarial corruption and heavy-tailed noise with finite (1+ϵ)-th moments for some ϵ∈ (0,1]. Existing work that addresses both adversarial corruption and heavy-tailed noise relies on a finite variance assumption and suffers from computational inefficiency. We propose the first computationally efficient algorithm based on online mirror descent that is robust to both adversarial corruption and heavy-tailed noise. While the existing algorithm incurs 𝒪(tlog T) computational cost per round, our algorithm reduces this to 𝒪(1) per round. We establish an additive regret bound consisting of a term depending on the (1+ϵ)-moment bound of the noise and a term depending on the total amount of corruption. This bound unifies and extends previous guarantees for (generalized) linear contextual bandits under adversarial corruption and heavy-tailed noise. In particular, when ϵ = 1, it recovers existing guarantees under finite-variance assumptions. When no corruption is present, it achieves the same regret rate as existing results for linear contextual bandits with heavy-tailed noise in the general setting. Moreover, the algorithm requires only upper bounds on the noise moment and the total amount of corruption, while still guaranteeing sublinear regret.

UAI 2026

Particle Dynamics for Latent-Variable Energy-Based Models

Shiqin Tang, Shuxin Zhuang, Runsheng Yu, Rong Feng, Shujian Yu, Hongzong LI, Mingyang Zhao, Gaofeng Meng

Latent-variable energy-based models (LV-EBMs) assign a single normalized energy to joint pairs of observed data and latent variables, offering expressive generative modeling while capturing hidden structure. We recast maximum-likelihood training as a saddle problem over distributions on the latent and joint manifolds and view the inner updates as coupled Wasserstein gradient flows. The resulting algorithm alternates overdamped Langevin updates for a joint negative pool and for conditional latent particles with stochastic parameter ascent, requiring no discriminator or auxiliary networks. We prove existence and convergence under standard smoothness and dissipativity assumptions, with decay rates in KL divergence and Wasserstein-2 distance. The saddle-point view further yields an ELBO strictly tighter than bounds obtained with restricted amortized posteriors. Our method is evaluated on numerical approximations of physical systems and performs competitively against comparable approaches.

UAI 2026

Deep Spectral Learning of Embedded Latent Transfer Operators for Stochastic Dynamical Systems

Ryogo Tanaka, Yoshinobu Kawahara

We propose a spectral learning method for stochastic nonlinear dynamical systems represented with embedded latent transfer operators in deep feature spaces. We instantiate the method as Deep Spectral Encoder (DSE), an operator-based latent state-space model in which a time-invariant neural encoder implements learnable nonlinear feature maps from observations, and these features define Markovian latent states whose temporal evolution and observation mapping are described by the transfer and observation operators, respectively. Functional canonical correlation analysis in a learnable Galerkin-projected feature space provides state coordinates from past and future observations, and the two linear operators are estimated on the state coordinates as ridge-regularized closed-form solutions that coincide with Galerkin projections of the associated covariance operators. On this representation, we generalize sequential Bayesian filtering and Koopman spectral mode decomposition in feature space. Experiments on several scenarios show stable and superior performance with sequential Bayesian filtering and dynamic mode decomposition baselines even under noise and partial observability.

UAI 2026

Learning Who to Treat When Treatment is Missing

Johnna Sundberg, Rayid Ghani, Eli Ben-Michael, Edward Kennedy

Policy learning methods are increasingly used to inform treatment allocation under budget constraints. Most proposed methods assume complete treatment data, yet applications frequently suffer from missingness that can bias estimates and lead to suboptimal policies. We address this gap by extending efficient estimators for average treatment effect (ATE) estimation to policy value and conditional average treatment effect (CATE) estimation under missing at random (MAR) and missing completely conditionally at random (MCCAR) treatment data. Through asymptotic efficiency analysis, we prove that the MAR estimator, which leverages partially-observed units, is both valid and more efficient than the MCCAR estimator when MCCAR assumptions hold. This result provides formal justification for preferring MAR-based estimation in policy learning under both missing data settings. Our comprehensive experiments using synthetic and semi-synthetic datasets confirm that correctly specifying the missingness mechanism is crucial: misspecified estimators remain biased regardless of sample size, while our estimators achieve near-oracle performance when assumptions are satisfied. Our work provides practitioners with theoretically grounded, empirically validated tools for robust policy learning in the presence of missing treatment data.

UAI 2026

Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent

Yihang Sun, Huaijin Wang, Patrick Hayden, Jose Blanchet

We present the first analytical study of ECD, focusing on the one-dimensional setting for this first installment. We formalize a stochastic ECD dynamics (sECD) with energy-preserving noise, as well as a quantum analog of the ECD Hamiltonian (qECD), providing the foundation for a quantum algorithm through Hamiltonian simulation in a tractable model where the barrier-crossing mechanism can be computed explicitly. For one-dimensional double-well objectives in the under-guessing regime, we compute the expected dynamical hitting times from a local minimum to the global minimum. We prove that both sECD and qECD exhibit exponential improvements in continuous hitting time relative to their respective gradient-based baselines, stochastic gradient descent (SGD) and quantum tunneling walk (QTW). For objectives with tall barriers, qECD admits a further hitting time improvement over sECD. Mechanistically, ECD sidesteps the exponential cost associated with rare-escape events of SGD from local minima by moving from dissipative to energy-conserving dynamics.

UAI 2026

Possibilistic Instrumental Variable Regression with Potentially Invalid Instruments

Gregor Steiner, Jeremie Houssineau, Mark Steel

Instrumental variable regression is a common approach for causal inference in the presence of unobserved confounding. However, identifying valid instruments is often difficult in practice. In this paper, we propose a novel method based on possibility theory that performs posterior inference on the treatment effect, conditional on a user-specified set of potential violations of the instrument exogeneity assumption. Our method can provide valid results even when only a single, potentially invalid, instrument is available. Crucially, and in contrast with existing methods, we prove a finite-sample coverage guarantee for the exactly calibrated (validified) uncertainty intervals when the violation set contains the true value, and we provide practical MC/χ^2 approximations. Simulation experiments and real-data applications indicate strong performance of the proposed approach.

UAI 2026

Multiwinner Voting with Interval Preferences under Incomplete Information

Drew Springham, Edith Elkind, Bart De Keijzer, Maria Polukarov

In multiwinner approval elections with many candidates, voters may struggle to determine their preferences over the entire slate of candidates. It is therefore of interest to explore which (if any) fairness guarantees can be provided under reduced communication. In this paper, we consider voters with one-dimensional preferences: voters and candidates are associated with points in ℝ, and each voter’s approval set forms an interval of ℝ. We put forward a probabilistic preference model, where the voter set consists of different groups; each group is associated with a distribution over an interval of ℝ, so that each voter draws the endpoints of her approval interval from the distribution associated with her group. We present an algorithm for computing committees that provide Proportional Justified Representation + (PJR+), which proceeds by querying voters’ preferences, and show that, in expectation, it makes 𝒪(log k) queries per voter, where k is the desired committee size.

UAI 2026

Privacy-Preserving Robustness Verification for Neural Networks

Nianyun Song, Xiaokun Luan, Yu Guo, Rongfang Bie, Meng Sun, Xiyue Zhang

Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual property constraints. This tension has left robustness verification impractical in privacy-sensitive domains. In this work, we address this gap with SecureCROWN, the first framework for privacy-preserving neural network robustness verification. Built upon secure two-party computation (2PC), our framework enables a model owner and a data owner to jointly compute certified robustness bounds—revealing only the final result while provably protecting both parties’ private data under the semi-honest security model. A key challenge is securely computing the conditional operations in Linear Bound Propagation, where the data-dependent branching is incompatible with standard secure computation protocols. We eliminate branching by formulating conditional logic as continuous arithmetic operations. Additionally, we introduce a Newton–Raphson refinement method to improve numerical stability. Extensive analysis and experiments show that SecureCROWN strictly matches plaintext verification results, while completing in 0.1–200s across varied model sizes and communication settings (LAN/WAN), demonstrating the feasibility of privacy-preserving neural network verification.

UAI 2026

Adaptive Fourier Decomposition-guided Neural Operator Design for Inverse PDE Problems

Zeyuan Song, Xiaocong Zhen, Zheyu Jiang

Inverse problems, which are generally ill-posed, aim to identify the unknown parameters of a physical system from the observations of its output. A large class of inverse problems for partial differential equations (PDEs) are only well-defined as mappings from operators to functions. However, existing operator learning frameworks either do not explicitly account for the underlying operator space or solve the inverse problems in a Hilbert space. Meanwhile, it has been shown that a Banach space setting for the parameter space would be closer to reality for a wide range of problems. Driven by this, we introduce AFDONet-inv, a novel neural operator solver whose design is rigorously guided by adaptive Fourier decomposition (AFD) theory, to solve inverse problems for PDEs in a Banach space. Each component of AFDONet-inv’s architecture, including primal and dual nets, latent-to-RKBS (reproducing kernel Banach space) network, and dynamic convolutional kernel network (CKN), has a corresponding component in the AFD operation in Banach space. This way, AFDONet-inv is mathematically explainable and grounded in the AFD theory and possesses several desirable properties. Extensive experiments demonstrate that AFDONet-inv outperforms state-of-the-art inverse PDE solvers in terms of solution accuracy.

UAI 2026

Consensus Optimization Graph Neural Networks

Olga Solodova, Ryan P Adams

Implicit graph neural networks (GNNs) cast inference as optimization, computing node embeddings as the solution to a graph-structured optimization problem. By coupling node embeddings through a shared global objective, implicit GNNs naturally capture long-range dependencies, addressing a key limitation of standard message-passing GNNs. Another appealing property of these models is that inference can be performed in a decentralized and asynchronous manner, making them well suited for deployment in multi-agent systems. However, training is costly, as it requires solving optimization problems in both the forward and backward pass. In this work, we focus on graph-level prediction and introduce an approach for directly computing graph-level representations in implicit GNNs that bypasses the need for node embeddings. We do this by reformulating the internal optimization problem to operate over a shared graph embedding. This significantly reduces both computation and memory costs, while retaining compatibility with decentralized and asynchronous inference. Experiments across multiple benchmarks show that the shared-embedding approach consistently matches the predictive performance of using node embeddings, providing a simpler and more efficient alternative for graph-level tasks.

UAI 2026

Learning-based Optimal Admission Control for Erlang-B Queuing Systems

Shubhhi Singh, Shubhanshu Shekhar, Vijay G Subramanian

This paper studies a learning-based optimal admission control policy for an Erlang–B queuing system under partial observation. Only at each arrival, the dispatcher observes the current occupancy and decides whether to accept or reject the job. A completed job yields a fixed reward but incurs a cost proportional to the service duration. The objective is to design an admission control policy that maximizes the long-term average reward. The arrival and service rates are unknown, and unobserved departures complicate parameter estimation. The reward structure induces an asymmetry in the optimal decision across parameter regimes. We establish an instance-dependent asymptotic lower bound, explicitly dependent on the system parameters, demonstrating that the worst-case regret is logarithmic in the number of arrivals in one regime.

UAI 2026

The Minimal Search Space for Conditional Causal Bandits

Francisco N. F. Q. Simoes, Itai Feigenbaum, Mehdi Dastani, Thijs van Ommen

Causal knowledge can be used to support decision-making problems. This has been recognized in the causal bandits literature, where a causal (multi-armed) bandit is characterized by a causal graphical model and a target variable. The arms are then interventions on the causal model, and rewards are samples of the target variable. Causal bandits were originally studied with a focus on hard interventions. We focus instead on cases where the arms are conditional interventions, which more accurately model many real-world decision-making problems by allowing the value of the intervened variable to be chosen based on the observed values of other variables. This paper presents a graphical characterization of the minimal set of nodes guaranteed to contain the optimal conditional intervention, which maximizes the expected reward. We then propose an efficient algorithm with a time complexity of O(|V| + |E|) to identify this minimal set of nodes. We prove that the graphical characterization and the proposed algorithm are correct. Finally, we empirically demonstrate that our algorithm significantly prunes the search space and substantially accelerates convergence rates when integrated into standard multi-armed bandit algorithms.

UAI 2026

Particle GFlowNets: Rethinking Generative Marginalization Models

Tiago da Silva, Diego Mesquita, Salem Lahlou

Generative Marginalization Models (MaMs) have been recently introduced as efficient neural sampling models for any-order autoregressive modelling of discrete distributions. By learning both the marginal and conditional probabilities of a persistent-block Gibbs sampler, MaMs enable fast posterior evaluation with a single neural network forward pass. While prior work has considered MaMs to be distinct from Generative Flow Networks (GFlowNets), a well-established paradigm for inference in discrete stochastic models, we show that they are equivalent. Then, we also extend MaMs’ sampling strategy to non-autoregressive generative processes. In particular, we describe an automatic criterion for full-state rejuvenation of the Gibbs sampler, derived from the Gelman-Rubin statistic, which plays a key role in speeding up learning convergence. Our experiments show that our method, called Particle GFlowNets, markedly accelerates training in large combinatorial spaces.

UAI 2026

A Stronger Calculus of Intervention for Max-Linear Bayesian Networks

Leon Sierau, Francesco Nowell, Nihat Ay

Max-linear Bayesian networks (MLBNs) are a novel class of directed acyclic graphical models which are of interest to statistics and data science due to their relevance to causality and probabilistic inference, particularly of extreme events. Interestingly, MLBNs encode strictly more conditional independence than general structural causal models. Because of this, MLBNs are Markov to a strengthening of the d-separation criterion called ∗-separation. As many tools for causal inference (most notably, Judea Pearl’s do-calculus) are based on d-separation, we address the natural question of whether assuming Markovianity to ∗-separation can lead to additional causal effect identifiability under intervention. We answer this question in the affirmative and develop a stronger version of the do-calculus rules for models which are Markov to ∗-separation. However, we note that restrictions inherent to the max-linear setting (in particular, that they give rise to non strictly positive joint probability distributions) mean that our calculus is only applicable to specific kinds of policy intervention.

UAI 2026

Conditional neural control variates for variance reduction in Bayesian inverse problems

Ali Siahkoohi, Hyunwoo Oh

Bayesian inference for inverse problems involves computing expectations under posterior distributions–e.g., posterior means, variances, or predictive quantities–typically via Monte Carlo (MC) estimation. When the quantity of interest varies significantly under the posterior, accurate estimates demand many samples–a cost often prohibitive for partial differential equation-constrained problems. To address this challenge, we introduce conditional neural control variates, a modular method that learns amortized control variates from joint model-data samples to reduce the variance of MC estimators. To scale to high-dimensional problems, we leverage Stein’s identity to design an architecture based on an ensemble of hierarchical coupling layers with tractable Jacobian trace computation. Training requires: (i) samples from the joint distribution of unknown parameters and observed data; and (ii) the posterior score function, which can be computed from physics-based likelihood evaluations, neural operator surrogates, or learned generative models such as conditional normalizing flows. Once trained, the control variates generalize across observations without retraining. We validate our approach on stylized and partial differential equation-constrained Darcy flow inverse problems, outperforming classical Stein control variates and achieving substantial variance reduction, even when the analytical score is replaced by a learned surrogate.

Keep browsing

More papers from top AI conferences

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