[edit]
Volume 272: Algorithmic Learning Theory, 24-27 February 2025, Politecnico di Milano, Milan, Italy
[edit]
Editors: Gautam Kamath, Po-Ling Loh
Generalization bounds for mixing processes via delayed online-to-PAC conversions
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:23-40
;Algorithmic Learning Theory 2025: Preface
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1-3
;[abs][Download PDF]
When and why randomised exploration works (in linear bandits)
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:4-22
;Agnostic Private Density Estimation for GMMs via List Global Stability
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:41-66
;Refining the Sample Complexity of Comparative Learning
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:67-88
;Understanding Aggregations of Proper Learners in Multiclass Classification
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:89-111
;Proper Learnability and the Role of Unlabeled Data
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:112-133
;Sample Compression Scheme Reductions
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:134-162
;Strategyproof Learning with Advice
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:163-166
;Cost-Free Fairness in Online Correlation Clustering
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:167-203
;Non-stochastic Bandits With Evolving Observations
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:204-227
;Nearly-tight Approximation Guarantees for the Improving Multi-Armed Bandits Problem
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:228-245
;A Model for Combinatorial Dictionary Learning and Inference
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:246-288
;Differentially Private Multi-Sampling from Distributions
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:289-314
;Near-Optimal Rates for O(1)-Smooth DP-SCO with a Single Epoch and Large Batches
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:315-348
;Generalisation under gradient descent via deterministic PAC-Bayes
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:349-389
;Boosting, Voting Classifiers and Randomized Sample Compression Schemes
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:390-404
;Effective Littlestone dimension
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:405-417
;Is Transductive Learning Equivalent to PAC Learning?
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:418-443
;Full Swap Regret and Discretized Calibration
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:444-480
;A PAC-Bayesian Link Between Generalisation and Flat Minima
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:481-511
;Reliable Active Apprenticeship Learning
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:512-538
;For Universal Multiclass Online Learning, Bandit Feedback and Full Supervision are Equivalent
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:539-559
;A Complete Characterization of Learnability for Stochastic Noisy Bandits
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:560-577
;Efficient Optimal PAC Learning
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:578-580
;Do PAC-Learners Learn the Marginal Distribution?
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:581-610
;Optimal and learned algorithms for the online list update problem with Zipfian accesses
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:611-648
;Information-Theoretic Guarantees for Recovering Low-Rank Tensors from Symmetric Rank-One Measurements
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:649-652
;Sharp bounds on aggregate expert error
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:653-663
;Quantile Multi-Armed Bandits with 1-bit Feedback
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:664-699
;On the Hardness of Learning One Hidden Layer Neural Networks
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:700-701
;Minimax-optimal and Locally-adaptive Online Nonparametric Regression
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:702-735
;Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:736-770
;Computationally efficient reductions between some statistical models
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:771-771
;Enhanced H-Consistency Bounds
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:772-813
;Center-Based Approximation of a Drifting Distribution
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:814-845
;Fast Convergence of Φ-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:846-869
;A Characterization of List Regression
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:870-920
;On Generalization Bounds for Neural Networks with Low Rank Layers
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:921-936
;Data Dependent Regret Bounds for Online Portfolio Selection with Predicted Returns
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:937-984
;A Unified Theory of Supervised Online Learnability
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:985-1007
;An Online Feasible Point Method for Benign Generalized Nash Equilibrium Problems.
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1008-1040
;The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1041-1107
;Efficient PAC Learning of Halfspaces with Constant Malicious Noise Rate
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1108-1137
;Self-Directed Node Classification on Graphs
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1138-1168
;High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1169-1220
;Clustering with bandit feedback: breaking down the computation/information gap
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1221-1284
;Online Learning of Quantum States with Logarithmic Loss via VB-FTRL
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1285-1312
;Noisy Computing of the Threshold Function
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1313-1315
;How rotation invariant algorithms are fooled by noise on sparse targets
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1316-1360
;Logarithmic Regret for Unconstrained Submodular Maximization Stochastic Bandit
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1361-1385
;The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis
Proceedings of The 36th International Conference on Algorithmic Learning Theory, PMLR 272:1386-1387
;subscribe via RSS