Regret-Optimal Wasserstein-Robust Regression

Sloan Nietert, Daniel Kuhn

Cost-Aware Learning

Clara Mohri, Amir Globerson, Haim Kaplan, Tomer Koren, Yishay Mansour

Multi-hypothesis learning to deal with conflicts

Tamara Drucks, Patrick Indri, Sebastian Heil

The binned k secretary problem

Laura Skovbæk, Yevgeny Seldin

Paired Counterfactual Auditing of Clinical Bias Propagation in Federated Pediatric Regression

Tirathraj Ramburn

Theoretical Behaviour of AI Agent Reasoning: From Generalisability to Rationality

Fengxiang He

ICML 2026

GOGH: Correlation-Guided Orchestration of GPUs in Heterogeneous Clusters

Ahmad raeisi, M. Sadegh Talebi, Mahdi Dolati, Sina Darabi, Patrick Eugster, Ahmad Khonsari

Green Scheduling of AI-training

Mathias Gilje, Laura Skovbæk, Yevgeny Seldin

Regret in Probabilistic Reward Machines

Hippolyte Bourel, Chenxiao Ma, Anders Jonsson, Odalric-Ambrym Maillard, M. Sadegh Talebi

A Single Stepsize for Robust and Fast Unprojected TD(0)

Wei-Cheng Lee, Francesco Orabona

COLT 2026

Teaching Partial Concept Classes

Rex Lei, Shay Moran, Hans U. Simon, Maximilian Thiessen, Sandra Zilles

PALM – A Predictive Model for Evaluating Sample Efficiency in Active Learning Models

Julia Machnio, Mads Nielsen, Mostafa Mehdipour Ghazi

ICCV 2025

The interplay of data structure and imbalance in the learning dynamics of diffusion models

Flavio Nicoletti, Chenxiao Ma, Enrico Ventura, Luca Saglietti, Stefano Sarao Mannelli

LoRA and Privacy: When Random Projections Help (and When They Don’t)

Yaxi Hu, Johanna Düngler, Bernhard Schölkopf, Amartya Sanyal

TPDP 2026

Less Noise, Same Certificate: Retain Sensitivity for Unlearning

Carolin Heinzler, Kasra Malihi, Amartya Sanyal

TPDP 2026

Language Generation with Replay: A Learning-Theoretic View of Model Collapse

Giorgio Racca, Michal Valko, Amartya Sanyal

ICML 2026

Why Forget only Unlearning needs Memorization

Luka Radić, Vikrant Singhal, Amartya Sanyal

Morphological Ambiguity and Sample Complexity in Arabic Hallucination Detection

Nsrin Ashraf

Analysis and Empirical Evaluation of δ-Regularized Gradient Clipping

Katsiaryna Novikava, Anna Lytova, Omar Rivasplata

Residual Privacy Budgeting with Weighted Scarcity Allocation for Online Query Answering

Mina Khoshmehr, Fernando Beltran

Community Recovery from Non-Binary Interactions: Information Limit, Optimal Algorithm, Preprocessing

Maximilien Dreveton

PAC-Bayesian Structural Risk Minimization

Aleksandr Karakulev, Prashant Singh

r-Adjacency Differential Privacy: Convex Learning, Gaussian Release, and Reconstruction Robustness

Joseph Margaryan, Nirupam Gupta

Concurrent Composition for Differentially Private Continual Mechanisms

Monika Henzinger, Roodabeh Safavi, Salil Vadhan

PODS 2026

CP-POL + PPI: Conformal Guarantees in Partially-Observed Label Space

Christian NGNIE

TMLR

How Private Is Each Token? Auditing Differential Privacy in Autoregressive Text Generation

Dhruv Shah, Vishnu Vinod, Krishna Pillutla

On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents

Oliver Mortensen, M. Sadegh Talebi

RLC 2026

(Semi-)Adversarial Causal Bandits with Known Causal Mechanism and Causal Self-Bounding

Hubert Marek Drazkowski, Yevgeny Seldin

Disagreement-Regularized Importance Sampling for Adversarial Label Corruption

Csongor Horváth, Prashant Singh, Ida-Maria Sintorn

Improved Accuracy for Private Continual Cardinality Estimation in Fully Dynamic Streams

Joel Daniel Andersson, Palak Jain, Satchit Sivakumar

PODS 2026

Near-Optimal Generalized Private Testing

Anamay Chaturvedi, Monika Henzinger, Jalaj Upadhyay

When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation

John Lazarsfeld

Towards PAC-Bayesian Guarantees for Self-Certified Fair Classification

Julien Bastian, Benjamin Leblanc, Pascal Germain, Amaury Habrard, Christine Largeron, Guillaume Metzler, Emilie Morvant, Paul Viallard

Learning Nash equilibria using Minorization-Majorization

Ashok Krishnan K.S., Helene Le Cadre, Ana Busic

Uncertainty Quantification for Calibrated Point Predictions

Georgios Gavrilopoulos, Johanna Ziegel

The Query Complexity of Local Search in Rounds on General Graphs

Simina Branzei, Ioannis Panageas, Dimitris Paparas

Adaptive Symmetrization of the KL Divergence

Omri Ben-Dov, Luiz F. O. Chamon

A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Rates

Alexander Ryabchenko, Idan Attias, Daniel M. Roy

Optimizing Dimensionality Reduction in SDN: A Metaheuristic Approach of UMAP Parameter Tuning

Abderrahmane JOUILILI

CIEES 2024

Inceptive RAG: A Rigorous Gradient-Based Attribution Metric for Programmatic Data Monetization

Doohee You