| 2026 | Truly Adapting to Adversarial Constraints in Constrained MABs. | Francesco Emanuele Stradi, Kalana Kalupahana, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti |
| 2026 | Privately Estimating Black-Box Statistics. | Gnter F. Steinke, Thomas Steinke |
| 2026 | Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment. | Ved Sriraman, Adam Block |
| 2026 | Efficient Learning and Symmetry Discovery under Exact Invariances. | Ashkan Soleymani, Behrooz Tahmasebi, Patrick Jaillet, Stefanie Jegelka |
| 2026 | Finite Sample Bounds for Learning with Score Matching. | Devin Smedira, Abhijith Jayakumar, Sidhant Misra, Marc Vuffray, Andrey Y. Lokhov |
| 2026 | Testing for a Hidden Geometry in Random Graphs. | Amit Silber, Mor Oren-Loberman, Wasim Huleihel |
| 2026 | Optimal Sample Complexity Lower Bounds on Conditional Independence Testing. | Jan Seyfried, Neelkanth Mishra, Sayantan Sen, Marco Tomamichel |
| 2026 | The Hidden Cost of Approximation in Online Mirror Descent. | Ofir Schlisselberg, Uri Sherman, Tomer Koren, Yishay Mansour |
| 2026 | Convergence of Continual Learning in Homogeneous Deep Networks. | Matan Schliserman, Gon Buzaglo, Itay Evron, Daniel Soudry |
| 2026 | A Depth Hierarchy for Computing the Maximum in ReLU Networks via Extremal Graph Theory. | Itay Safran |
| 2026 | Private Linear Regression via a Down-Sensitivity to Privacy Reduction. | Ittai Rubinstein, Chris Ge, Samuel B. Hopkins |
| 2026 | Continuous time policy evaluation is easier with noisy dynamics. | Samuel Robertson, Thomas Newton, Csaba Szepesvri |
| 2026 | Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining. | Yunwei Ren, Yatin Dandi, Florent Krzakala, Jason D. Lee |
| 2026 | Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum. | Nived Rajaraman, Audrey Huang, Miro Dudk, Robert E. Schapire, Dylan J. Foster, Akshay Krishnamurthy |
| 2026 | Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach. | Hao Qiu, Mengxiao Zhang, Nicol Cesa-Bianchi |
| 2026 | Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits. | Hao Qin, Chicheng Zhang |
| 2026 | Deep Q-Learning on Hlder Spaces. | Qian Qi |
| 2026 | Boosting with List-Decodable Codes. | Addison Prairie, Li-Yang Tan |
| 2026 | Spectral Recovery of a Planted Triangle-Dense Subgraph. | Sam van der Poel, Cheng Mao, Benjamin McKenna |
| 2026 | An Exponential Lower Bound for Spectral Density Estimation on Unweighted Graphs. | Pan Peng, Yuyang Wang, Joy Qiping Yang, Yichun Yang |
| 2026 | Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift. | Shyamal Patel, Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan |
| 2026 | Invited Open Problem: Does Differential Privacy Make PAC Learning Much Harder? | Kobbi Nissim, Uri Stemmer, Eliad Tsfadia |
| 2026 | Graph neural networks extrapolate out-of-distribution for shortest paths. | Robert R. Nerem, Samantha Chen, Sanjoy Dasgupta, Yusu Wang |
| 2026 | Optimal Neural Network Approximation of Smooth Compositional Functions on Sets with Low Intrinsic Dimension. | Thomas Nagler, Sophie Langer |
| 2026 | Minimax Limits of k-Fold Cross-Validation via Majority. | Ido Nachum, Rdiger L. Urbanke, Thomas Weinberger |