AISTATS 2026 Monday 05/4

$\epsilon$-Identifiability of Causal Quantities

Ang Li · Scott Mueller · Xin Shu · Judea Pearl

ACE-KT: Cascaded Cognitive Modeling for Stage-wise Knowledge Tracing

Teng Guo · Yubin Xia · Jinsen Ke · Mingliang Hou · Jiaqi Zheng · Zitao Liu

Learning to Explore with Lagrangians for Bandits under Unknown Constraints

Udvas Das · Debabrota Basu

Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners

Tinashe Handina · Tongxin Li · Kishan Panaganti · Eric Mazumdar · Adam Wierman

LLM-as-a-Judge on a Budget

Aadirupa Saha · Aniket Wagde · Branislav Kveton

Longitudinal Flow Matching for Trajectory Modeling

Mohammad Mohaiminul Islam · Coen de Vente · Sharvaree Vadgama · Thijs Kuipers · Afsana Khan · Clara Sánchez · Erik Bekkers

Meta-probabilistic Modeling

Kevin Zhang · Yixin Wang

MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning

Hasin Us Sami · Swapneel Sen · Basak Guler

Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games

Alireza Masoumian · James Wright

Model-independent O(1/k)-convergence rate for TD(0) with linear function approximation, universal learning steps and i.i.d. samples

Ziad Kobeissi · Eloïse Berthier

Modeling Multi-Objective Tradeoffs with Monotonic Utility Functions

Edward Chen · Natalie Dullerud · Thomas Niedermayr · Elizabeth Kidd · Ransalu Senanayake · Pang Wei Koh · Sanmi Koyejo · Carlos Guestrin

Monotone and Conservative Policy Iteration Beyond the Tabular Case

S R Eshwar · Gugan Chandrashekhar Mallika Thoppe · Ananyabrata Barua · Aditya Gopalan · Gal Dalal

Active Measurement of Two-Point Correlations

Max Hamilton · Daniel Sheldon · Subhransu Maji

Multi-Agent Lipschitz Bandits

Sourav Chakraborty · Amit Rege · Lijun Chen · Claire Monteleoni

Multi-Armed Sampling Problem and the End of Exploration

Mohammad Pedramfar · Siamak Ravanbakhsh

Multiclass Local Calibration with the Jensen-Shannon Distance

Cesare Barbera · Lorenzo Perini · Giovanni De Toni · Andrea Passerini · Andrea Pugnana

Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs

Hee-Jun Jung · Jaehyoung Jeong · Kangil Kim

Near Optimal Dropout-Robust Sortion

Maya Gambhir · Bailey Flanigan · Aaron Roth

Nearly Optimal Best Arm Identification for Semiparametric Bandits

Seok-Jin Kim

Network Inversion for Extreme-Case Training-Like Data Reconstruction

Pirzada Suhail · Sunny Gupta · Amit Sethi

Non-Stationary Functional Bilevel Optimization

Jason Bohne · Ieva Petrulionytė · Michael Arbel · Julien Mairal · Pawel Polak

Numerical Fragility in Transformers: A Layer-wise Theory for Explaining, Forecasting, and Mitigating Instability

Jinwoo Baek

OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation

Kanad Pardeshi · Bryan Wilder · Aarti Singh

Active Measuring in Reinforcement Learning With Delayed Negative Effects

Daiqi Gao · Ziping Xu · Aseel Rawashdeh · Predrag Klasnja · Susan Murphy

On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous Environments

Safwan Labbi · Paul Mangold · Daniil Tiapkin · Eric Moulines

On propagation of chaos for the Fisher-Rao gradient flow in entropic mean-field optimization

Petra Lazić · Linshan Liu · Mateusz Majka

On the bias of variational resampling

Axel Finke · Oskar Kviman · Nicola Branchini · Victor Elvira

On the calibration of survival models with competing risks

Julie Alberge · Tristan Haugomat · Gaël Varoquaux · Judith Abécassis

On the convergence and straightness of flow matching models

Saptarshi Roy · Vansh Bansal · Purnamrita Sarkar · Alessandro Rinaldo

On the Finite-Sample Bias of Minimizing Expected Wasserstein Loss Between Empirical Distributions

Cheongjae Jang · Yung-Kyun Noh

On the Hardness of Auditing Model Properties Under Updates: Complexity of Property-Preserving Updates

Ayoub Ajarra · Debabrota Basu

On the Identifiability of Tensor Ranks via Prior Predictive Matching

Eliezer da Silva · Arto Klami · Diego Mesquita · Iñigo Urteaga

On the Intrinsic Dimensions of Data in Kernel Learning

Rustem Takhanov

On the Neural Feature Ansatz for Deep Neural Networks

Edward Tansley · Estelle Massart · Coralia Cartis

Adaptive A/B Testing under Nonstationary Dynamics using State-Space Models

Junzhe Shao · Waverly Wei · Jingshen Wang

On the Normalization of Confusion Matrices: Methods and Geometric Interpretations

Johan Erbani · Sonia Ben Mokhtar · Pierre-Edouard Portier · Elöd Egyed-Zsigmond · Diana Nurbakova

On the Number of Conditional Independence Tests in Constraint-based Causal Discovery

Marc Franquesa Monés · Jiaqi Zhang · Caroline Uhler

One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow

Pascal Dube · Jiaru Zhang · Ziran Wang · Ruqi Zhang

Open Multi-agent Multi-armed Bandit with Applications in Permissionless Blockchain

Mengfan Xu · Diego Klabjan

Optimal Learning in Two-Player Zero-Sum Games under Delayed Feedback

Ruotong Zhuang · Taira Tsuchiya · Shinji Ito

Optimal Transport Guarantees to Nonparametric Regression for Locally Stationary Time Series

Jan Nino Tinio · Mokhtar Alaya · Salim Bouzebda

Optimistic Reinforcement Learning with Quantile Objectives

Mohammad Alipour-Vaezi · Huaiyang Zhong · Kwok-leung Tsui · Sajad Khodadadian

Optimized projection-free algorithms for online learning: construction and worst-case analysis

Julien Weibel · Pierre Gaillard · Wouter Koolen · Adrien Taylor

Orthogonal Representation Learning for Estimating Causal Quantities

Valentyn Melnychuk · Dennis Frauen · Jonas Schweisthal · Stefan Feuerriegel

Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective

Soo Min Kwon · Alec Xu · Can Yaras · Laura Balzano · Qing Qu

Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization

Donney Fan · Geoff Pleiss

Panprediction: Optimal Predictions for Any Downstream Task and Loss

Sivaraman Balakrishnan · Nika Haghtalab · Daniel Hsu · Brian Lee · Eric Zhao

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation

Neeraj Gangwar · Anshuka Rangi · Rishabh Deshmukh · Holakou Rahmanian · Yesh Dattatreya · Nickvash Kani

Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection

Hassan Baker · Austin J. Brockmeier

PolarQuant: Vector Quantization with Polar Transformation

Amir Zandieh · Praneeth Kacham · Insu Han · Vahab Mirrokni · Amin Karbasi

Policy Learning with Abstention

Ayush Sawarni · Jikai Jin · Justin Whitehouse · Vasilis Syrgkanis

PowerSoftmax: Towards Secure LLM Inference Over Encrypted Data

Itamar Zimerman · Allon Adir · Ehud Aharoni · Matan Avitan · Moran Baruch · Nir Drucker · Jenny Lerner · Ramy Masalha · Reut Moshe · Omri Soceanu

Predictive Deep Sets

Alex Hämäläinen · Sammie Katt · Samuel Kaski

Private, Efficient, and Robust Federated Statistical Learning

Jaemu Heo · Xiwen Feng · Jeonghun Kang · Taehwan Kim · Changgee Chang

Proof of The TAP Free Energy for High-Dimensional Linear Regression with Spherical Priors at All Temperatures

Zhiyuan Yu · Jingbo Liu

Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors

Zhiwei Han · Stefan Matthes · Hao Shen

Adaptive Diffusion Guidance via Stochastic Optimal Control

Iskander Azangulov · Peter Potaptchik · Qinyu Li · Eddie Aamari · George Deligiannidis · Judith Rousseau

Provable FDR Control for Deep Feature Selection: Arbitrarily Deep MLPs and Transformers

Kazuma Sawaya

ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers

Shivam Patel · Neharika Jali · Ankur Mallick · Gauri Joshi

Q-Learning with Shift-Aware Upper Confidence Bound in Non-Stationary Reinforcement Learning

Ha Manh Bui · Felix Parker · Kimia Ghobadi · Anqi Liu

Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning

Hoang Ngo · Nhat Hoang-Xuan · Quan Nguyen · Nguyen Do · Incheol Shin · My T. Thai

Quantifying Epistemic Uncertainty in Diffusion Models

Aditi Gupta · Raphael Meyer · Yotam Yaniv · Elynn Chen · N. Benjamin Erichson

RamPINN: Recovering Raman Spectra From Coherent Anti-Stokes Spectra Using Embedded Physics

Sai Karthikeya Vemuri · Adithya Ashok Chalain Valapil · Tim Büchner · Joachim Denzler

Randomized HyperSteiner: A Stochastic Delaunay Triangulation Heuristic for the Hyperbolic Steiner Minimal Tree

Aniss Aiman Medbouhi · Alejandro García-Castellanos · Giovanni Luca Marchetti · Daniel Pelt · Erik Bekkers · Danica Kragic

RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection

Haim Zisman · Uri Shaham

Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights

Liangzu Peng · Uday Kiran Reddy Tadipatri · Ziqing Xu · Eric Eaton · Rene Vidal

Refining Covariance Matrix Estimation in Stochastic Gradient Descent through Bias Reduction

Ziyang Wei · Wanrong Zhu · Jingyang Lyu · Wei Biao Wu

Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization

Kristi Topollai · Anna Choromanska

Regression Descent: A Statistical Framework for Neural Network Optimization

Kamaljeet Singh · Nicolas Hengartner · Hao Zhang · Brian Bell · James Hyman

Regularized $f-$Divergence Kernel Tests

Arthur Gretton · Mónica Ribero · Antonin Schrab

Regularizing attention scores with the bootstrapping

Maxim Laletin · Neo Christopher Chung

Replicable Machine Learning: Theory and Algorithms for Stochastic Convex and Non-Convex Optimization

Raman Arora · Kaibo Zhang

Retrieval Augmented Time Series Forecasting

Kutay Tire · Ege Taga · Muhammed Emrullah Ildiz · Samet Oymak

Robust Federated Clustering under Heterogeneity and Adversaries

Martín Bravo · Sebastian Dalleiger

Robust Learning of A Group DRO Neuron

Guyang Cao · Shuyao Li · Sushrut Karmalkar · Jelena Diakonikolas

Robustness and Generalization in Uncertainty-Aware Message Passing Neural Networks

Alesia Chernikova · Moritz Laber · Narayan G. Sabhahit · Tina Eliassi-Rad

Scalable Policy Maximization Under Network Interference

Aidan Gleich · Eric Laber · Alexander Volfovsky

Scalable Utility-Aware Multiclass Calibration

Mahmoud Hegazy · Michael Jordan · Aymeric Dieuleveut

Adversarial Debiasing for Parameter Recovery

Luke Sanford · Megan Ayers · Matthew Gordon · Eliana Stone

Securing Model Weights against Eavesdropping Adversaries in Federated Learning using Quantization

Kushal Chakrabarti · Dipankar Maity

SetPINNs: Set-based Physics-informed Neural Networks

Mayank Nagda · Phil Ostheimer · Thomas Specht · Frank Rhein · Fabian Jirasek · Stephan Mandt · Marius Kloft · Sophie Fellenz

Shift is Good: Mismatched Data Mixing Improves Test Performance

Marko Medvedev · Kaifeng Lyu · Zhiyuan Li · Nathan Srebro

Simplex-to-Euclidean Bijections for Categorical Flow Matching

Bernardo Williams · Victor Yeom-Song · Marcelo Hartmann · Arto Klami

Slithering through Gaps: Capturing Discrete Isolated Modes via Logistic Bridging

Pinaki Mohanty · Ruqi Zhang

Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting

Huu Hiep Nguyen · Minh Nguyen · Dung Nguyen · Hung Le

Spectral Thresholds in Correlated Spiked Models and Fundamental Limits of Partial Least Squares

Pierre Mergny · Lenka Zdeborova

SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features

Hyeon Jun Lee · Hyeonsik Jo · Jinwoo Chung · Jangho Kim

TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer

Jiayu Li · Bingyin Zhao · Zilong Zhao · Uzair Javaid · Biplab Sikdar

TENDE: Transfer Entropy Neural Diffusion Estimation

Simon Munoz · Maurizio Filippone · Giulio Franzese · Mustapha Bounoua · Pietro Michiardi

Adversary-Free Counterfactual Prediction via Information-Regularized Representations

Shiqin Tang · Rong Feng · Shuxin Zhuang · Hongzong LI · Youzhi Zhang

TESLA: Taylor Expansion of Sinusoidal Learnable Activations

Daehwa Ko · Jay Hoon Jung · SeungHyun Ham · JaeHyeon Kim

TexTSC: Class-Texture Preserving Data Condensation for Time Series Classification

Pouya Hosseinzadeh · Peiyu Li · Omar Bahri · Soukaina Filali Boubrahimi · Shah Muhammad Hamdi

The Cross-Context Threshold Test: Detecting Discrimination Under Environmental Shifts

Jun Yuan · Xinyue Ye

The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification

Tavor Baharav · Spyridon Konstantinos Dragazis · Aldo Pacchiano

The Information Geometry of Local Generalization Dynamics

Emmanouil-Marios Athanasakos

The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem Solving

Max Ruiz Luyten · Mihaela van der Schaar

The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches

Vishesh Kumar · Akshay Agarwal

Three-Step Nav: A Hierarchical Global–Local Planner for Zero-Shot Vision-and-Language Navigation

Wanrong Zheng · Yunhao Ge · Laurent Itti

Time-series Diagnostic Reasoning with Knowledge Injection

Zelin He · Boran Han · Xiyuan Zhang · Shuai Zhang · Qi Zhu · Haoyang Fang · Danielle Maddix · Abdul Fatir Ansari · Haotian Lin · Akash Chandrayan · Abhinav Pradhan · Bernie Wang · Matthew Reimherr

Tractable Gaussian Phase Retrieval with Heavy Tails and Adversarial Corruption with Near-Linear Sample Complexity

Santanu Das · jatin batra

Aggregation on Learnable Manifolds for Asynchronous Federated Optimisation

Archie Licudi · Anshul Thakur · Soheila Molaei · Danielle Belgrave · David Clifton

Two mathematical models of knowledge distillation

Audrey Xie · Ludwig Schmidt · John Duchi

Uncovering Hidden Training Dynamics in Neural Networks via Inter-Sample Influence Graphs

Dylan Tai · Jiayin Zhang · Rohan Ghosh · Mehul Motani

Understanding SAM's Robustness to Noisy Labels through Gradient Down-weighting

Hoang-Chau Luong · Thuc Nguyen-Quang · Dat Tran · Minh-Triet Tran

Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks

Han Zhang · Yuan Cao

UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees

Prateek Chanda · Prayas Agrawal · Karthik Gurumoorthy · Ganesh Ramakrishnan · Bamdev Mishra · Pratik Jawanpuria

Value Gradient Sampler: Learning Invariant Value Functions for Equivariant Diffusion Sampling

Himchan Hwang · Hyeokju Jeong · Dong Shin · Che-Sang Park · Sehee Kweon · Sangwoong Yoon · Frank Park

VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference

Sakshi Agarwal · Gabriel Hope · Jimin Heo · Erik B. Sudderth

Visual Prompting Reimagined: The Power of Activation Prompts

Yihua Zhang · Hongkang Li · Yuguang Yao · Aochuan Chen · Shuai Zhang · Pin-Yu Chen · Meng Wang · Sijia Liu

WSBD: Freezing-Based Optimizer for Quantum Neural Networks

Christopher Kverne · Mayur Akewar · Yuqian Huo · Tirthak Patel · Janki Bhimani

ZipMoE: A Theoretically-Grounded Mixture of Experts Approach forParameter-Efficient Deep Learning

Lin Chen · Kyriakos Axiotis · Gang Fu · Kaiyuan Wang · MohammadHossein Bateni · Vahab Mirrokni

A Continuous Time Markov Chain Framework for Insertion Language Models

Dhruvesh Patel · Benjamin Rozonoyer · Soumitra Das · Tahira Naseem · Tim G. J. Rudner · Andrew McCallum

Amortized In-Context Mixed Effect Transformer Models: A Zero-Shot Approach for Pharmacokinetics

César Ali Ojeda Marin · Niklas Hartung · Wilhelm Huisinga · Ramses Sanchez

Amortized Structural Variational Inference

Shitao Fan · Carlos Misael Madrid Padilla · Yun Yang · Lizhen Lin

AMRM-Pure: Semantic-Preserving Adversarial Purification

Zhihao Dou · Zhiqiang Gao · Dongfei Cui · Weida Wang · Qinjian Zhao · Zhang Dinggen · Jun Yan · Zeke Xie · Shufei Zhang

An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representation

Yichen Gao · Altay Unal · Akshay Rangamani · Zhihui Zhu

Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls

Nikolaos Nakis · Chrysoula Kosma · Panagiotis Promponas · Michail Chatzianastasis · Giannis Nikolentzos

Atlas-based Manifold Representations for Interpretable Riemannian Machine Learning

Ryan Robinett · Sophia Madejski · Kyle Ruark · Samantha Riesenfeld · Lorenzo Orecchia

Auditing Pay-Per-Token in Large Language Models

Ander Artola Velasco · Stratis Tsirtsis · Manuel Gomez Rodriguez

Auto-Regressive Masked Diffusion Models

Mahdi Karami · Ali Ghodsi

Bandits in Flux: Dynamic Regret under Adversarial Constraints

Tareq Si Salem

BASTION: A Bayesian Framework for Trend and Seasonality Decomposition

Jason Cho · David Matteson

A correlation analysis approach to finding interpretable latent representations via conditional generative models

James Buenfil · Eardi Lila

Batch-Adaptive Causal Annotations

Ezinne Nwankwo · Lauri Goldkind · Angela Zhou

Bayesian Fourier Features for Reduced Rank Gaussian Processes

Cristian A. Galvis-Florez · George Whittle · Michael A. Osborne · Simo Särkkä

Beyond Real Data: Synthetic Data through the Lens of Regularization

Amitis Shidani · Tyler Farghly · Yang SUN · Habib Ganjgahi · George Deligiannidis

Beyond Spectral Clustering: Probabilistic Cuts for Differentiable Graph Partitioning

Ayoub Ghriss

Beyond the Ideal: Analyzing the Inexact Muon Update

Egor Shulgin · AlRashed · Peter Richtarik · Francesco Orabona

Black-Box Optimization from Small Offline Datasets via Meta Learning with Synthetic Tasks

Azza Fadhel · The Hung Tran · Nghia Hoang · Jana Doppa

BOAT: Navigating The Sea of in Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization

Jackie Rao · Ferran Gonzalez · Leon Gerard · Alexandra Gessner

Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels

Marcel Bernal · Neil Mallinar · Mikhail Belkin

CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning

Mahyar Alinejad · Yue Wang · George Atia

Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs

Hen Davidov · Shai Feldman · Gilad Freidkin · Yaniv Romano

A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks

Sergio Calvo Ordoñez · Jonathan Plenk · Richard Bergna · Alvaro Cartea · Jose Miguel Hernandez-Lobato · Konstantina Palla · Kamil Ciosek

Calibrated Principal Component Regression

Yixuan Florence Wu · Yilun Zhu · Lei Cao · Naichen Shi

CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks

Mushir Akhtar · M. Tanveer · Mohd. Arshad

Clustering-Based Edge Augmentation for Minimizing the Kirchhoff Index

Prasanth Yalamanchili · Aditya Bhaskara

ConDiSim: Conditional Diffusion Models for Simulation-Based Inference

Mayank Nautiyal · Andreas Hellander · Prashant Singh

Confidence-Guided Self-Training for Domain Adaptation

Akram Heidarizadeh · Akram Awad · HanQin Cai · George Atia

Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise

Yuanjie Shi · Peihong Li · Zijian Zhang · Jana Doppa · Yan Yan

Contextual ranking and matching. Optimal regret under LST

Hafedh Ferchichi · Vianney Perchet · Matthieu LERASLE

Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria

Anas Barakat · Ioannis Panageas · Antonios Varvitsiotis

CoreSPECT: Enhancing Clustering Algorithms via an Interplay of Density and Geometry

Chandra Sekhar Mukherjee · Joonyoung Bae · Jiapeng Zhang

Counterfactually Fair Conformal Prediction

Ozgur Guldogan · Neeraj Sarna · Yuanyuan Li · Michael Berger

A New Perspective on Least-Norm Interpolation Under Gaussian Covariates

Gil Kur · Zong Shang · Paul Simanjuntak · Guillaume Lecué · Reese Pathak

Deep Feedback Models

David Calhas · Arlindo Oliveira

Deep Polynomial Chaos Expansion

Johannes Exenberger · Sascha Ranftl · Robert Peharz

Deliberate-When-Needed: Flow-Reasoner for Neuro-Symbolic Continuous Thought

Wenjie Shen · Boyang Li · Chao Yang · Shuang Li

Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves

Anand Jerry George · Rodrigo Veiga · Nicolas Macris

Differentially Private and Federated Structure Learning in Bayesian Networks

Ghita Fassy El Fehri · Aurélien Bellet · Philippe Bastien

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level

Saleh Khah · Savelii Chezhegov · Shahrokh Farahmand · Samuel Horvath · Eduard Gorbunov

Differentially Private Linear Regression and Synthetic Data Generation with Statistical Guarantees

Shurong Lin · Aleksandra Slavkovic · Deekshith Bhoomireddy

Direct Preference Optimization With Unobserved Preference Heterogeneity

Keertana Chidambaram · Karthik Seetharaman · Vasilis Syrgkanis

Discrete State Diffusion Models: A Sample Complexity Perspective

Aadithya Srikanth · Mudit · Vaneet Aggarwal

Disentangling Federated Learning Heterogeneity: A Dual-Perspective Analysis of Quantifying Skew versus Scarcity

Wenkai Zeng · NAN YANG · Zhiyu Zhu · Zhibo Jin · Dong Yuan

A Polynomial-Time Approximation for Pairwise Fair $k$-Median Clustering

Sayan Bandyapadhyay · Eden Chlamtáč · Zachary Friggstad · Mahya Jamshidian · Yury Makarychev · Ali Vakilian

Distribution free M-estimation

Felipe Areces · John Duchi

DP-SPRT: Differentially Private Sequential Probability Ratio Tests

Thomas Michel · Debabrota Basu · Emilie Kaufmann

DRAUN: An Optimization-Agnostic Data Reconstruction Attack on Federated Unlearning

Hithem Lamri · Manaar Alam · Haiyan Jiang · Michail Maniatakos

Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization

Tuo Liu · El Mehdi Saad · Wojciech Kotlowski · Francesco Orabona

Efficient Bilevel Optimization with KFAC-Based Hypergradients

Disen Liao · Felix Dangel · Yaoliang Yu

Efficient Flow Matching using Latent Variables

Anirban Samaddar · Yixuan Sun · Viktor Nilsson · Sandeep Madireddy

Efficient model performance evaluation using a combination of expert and crowd-sourced labels

Sam Corbett-Davies · Viet-An Nguyen · Udi Weinsberg

Eliciting Truthful Feedback for Preference-Based Learning via the VCG Mechanism

Leo Landolt · Anna Maddux · Andreas Schlaginhaufen · Saurabh Vaishampayan · Maryam Kamgarpour

Empirically Calibrated Conditional Independence Tests

Milleno Pan · Antoine de Mathelin · Wesley Tansey

Exact Tensor Completion Powered by Slim Transforms

Li Ge · Lin Chen · Yudong Chen · Xue Jiang

A Semi-Supervised Kernel Two-Sample Test

Gyumin Lee · Shubhanshu Shekhar · Ilmun Kim

Explicit Density Approximation for Neural Implicit Samplers Using a Bernstein-Based Convex Divergence

José Manuel de Frutos · Pablo Martínez Olmos · Manuel Vázquez · Joaquín Míguez

Fast Private Adaptive Query Answering for Large Data Domains

Miguel Fuentes · Brett Mullins · Yingtai Xiao · Daniel Kifer · Cameron Musco · Daniel Sheldon

Finite-Time Analysis of Gradient Descent for Shallow Transformers

Enes Arda · Semih Cayci · Atilla Eryilmaz

Frequency-Based Hyperparameter Selection in Games

Aniket Sanyal · Baraah Sidahmed · Rebekka Burkholz · Tatjana Chavdarova

From Counts to Preferences: Preference-Driven Models for Spatio-Temporal Event Data

Chao Yang · Yiling Kuang · Shuang Li

From Decision to Acquisition: Loss-Driven Bayesian Active Learning

Zhuoyue Huang · Freddie Bickford Smith · Tom Rainforth

From Restless to Contextual: A Thresholding Bandit Reformulation for Finite-horizon Improvement

Jiamin Xu · Ivan Nazarov · Aditya Rastogi · Africa Perianez Santiago · Kyra Gan

Functional Properties of the Focal-Entropy

Jaimin Shah · Martina Cardone · Alex Dytso

Fundamental limits for weighted empirical approximations of exponentially tilted distributions

Sarvesh Iyer · Himadri Mandal · Dhruman Gupta · Rushil Gupta · Agniv Bandyopadhyay · Achal Bassamboo · Sandeep Juneja · Varun Gupta

Generalization Bounds for Heavy-Tailed Losses

Gholamali Aminian

A Unifying Framework for Unsupervised Concept Extraction

Chandler Squires

Generalization Bounds for Spectral GNNs via Fourier Domain Analysis

Vahan Martirosyan · Daniele Malitesta · Hugues Talbot · Jhony Giraldo · Fragkiskos Malliaros

Gradient Descent with Provably Tuned Learning-rate Schedules

Dravyansh Sharma

GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations

Julia Herbinger · Gabriel Laberge · Maximilian Muschalik · Yann Pequignot · Marvin N. Wright · Fabian Fumagalli

Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts

Fangshuo Liao · Anastasios Kyrillidis

HGT-FD: Hypergraph transformer for Fraud Detection

Yintao Cai · Yunjiong Liu · Zelong Yang · Shuyang Fang · Xiaoping Min

High-Performance Self-Supervised Representation Learning by Joint Training of Flow Matching and Representation Encoder

Kosuke Ukita · Tsuyoshi Okita

High-Probability Bounds for Heterogeneous Local Differential Privacy

Maryam Aliakbarpour · Alireza Fallah · Swaha Roy · Ria Stevens

How to approximate inference with subtractive mixture models

Lena Zellinger · Nicola Branchini · Lennert De Smet · Victor Elvira · Nikolay Malkin · Antonio Vergari

Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression

Weiyi He · Yue Xing

Improving Adaptive Moment Optimization via Preconditioner Diagonalization

Son Nguyen · Bo Liu · Lizhang Chen · qiang liu

Accelerated Learning on Large Scale Screens using Generative Library Models

Eli Weinstein · Andrei Slabodkin · Mattia Gollub · Elizabeth Wood

In-memory Training on Analog Devices with Limited Conductance States via Multi-tile Residual Learning

Jindan Li · Zhaoxian Wu · Gaowen Liu · Tayfun Gokmen · Tianyi Chen

Inverse-Free Sparse Variational Gaussian Processes

Stefano Cortinovis · Laurence Aitchison · Stefanos Eleftheriadis · Mark van der Wilk

Is Supervised Learning Really That Different from Unsupervised?

Oskar Allerbo · Thomas Schön

It’s All In The (Exponential) Family: An Equivalence Between Maximum Likelihood Estimation and Control Variates For Sketching Algorithms

Keegan Kang · Kerong Wang · Ding Zhang · Rameshwar Pratap · Bhisham Verma · Benedict Wong

KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity

Damien Lesens · Beheshteh T. Rakhshan · Guillaume Rabusseau

Latent-IMH: Efficient Bayesian Inference for Inverse Problems with Approximate Operators

Youguang Chen · George Biros

Learning Equivariant Functions via Quadratic Forms

Pavan Karjol · Vivek Kashyap · Rohan Kashyap · Prathosh AP

Learning Linear Regression with Low-Rank Tasks in-Context

Kaito Takanami · Takashi Takahashi · Yoshiyuki Kabashima

Learning Markov Processes as Sum-of-Square Forms for Analytical Belief Propagation

Peter Amorese · Morteza Lahijanian

Learning Right Monotone Permutation Matrices for Neural Subsequence Search

Bhavya Kohli · Soutrik Sarangi · Aziz Shameem · Abir De

Main Navigation

Registration

Keynote: Taiji Suzuki

Oral Session 6: Generative Modeling (Diffusion / Flow / Temporal / Graph)

Oral Session 7: Causality, Kernels & Statistical Testing

Oral Session 8: Robustness, Calibration, Privacy & Evaluation (Applied)

Poster Session 3