arXiv Machine Learning
Jul 1
Calibeating for general proper losses: A Bregman divergence approach
arXiv:2605. 17269v2 Announce Type: replace Abstract: This work introduces a general framework for calibeating based on regret minimization.
Toward Simultaneously Optimal Regret in U-Calibration
arXiv:2606. 18527v1 Announce Type: cross Abstract: U-calibration studies online forecasting algorithms whose predictions can be consumed by any unknown downstream agent, guaranteeing sublinear regret simultaneously for all proper loss functions.
Related stories
arXiv Machine Learning
Jul 28
Gradient-Variation Regret Bounds for Unconstrained Online Learning
arXiv:2604. 11151v2 Announce Type: replace Abstract: We develop parameter-free algorithms for unconstrained online learning with regret guarantees that scale with the gradient variation $V_T(u) = \sum_{t=2}^T \|\nabla f_t(u)-\nabla f_{t-1}(u)\|^2$.
arXiv Machine Learning
Aug 12
High-Dimensional Calibration from Swap Regret
arXiv:2505. 21460v2 Announce Type: replace Abstract: We study online calibration of multi-dimensional forecasts over an arbitrary convex set $P \subset \mathbb{R}^d$ relative to an arbitrary norm $|\cdot|$.
arXiv Machine Learning
Aug 10
Dirichlet Follow-the-Leader Closes the Gap in Simultaneous Multiclass U-Calibration
arXiv:2608. 06656v1 Announce Type: new Abstract: Can one forecaster attain the optimal regret rate for every bounded proper loss and also adapt to every smooth proper loss?
arXiv Machine Learning
1d ago
Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits
arXiv:2510. 22819v3 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the learning process over time.
arXiv Machine Learning
Jul 23
Optimal Recalibration of an Online Predictor
arXiv:2607. 19689v1 Announce Type: cross Abstract: We study the problem of recalibrating an online predictor [KE17, OKS24]: given an arbitrary "hint" sequence of forecasts, the learner must output new predictions that are calibrated while incurring small excess error relative to the original forecasts, under a proper loss.
arXiv Machine Learning
Jul 1
Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions
arXiv:2606. 31769v1 Announce Type: new Abstract: We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees together with data-dependent regret bounds.
arXiv Machine Learning
Aug 4
A Perturbation Approach to Unconstrained Linear Bandits
arXiv:2603. 28201v3 Announce Type: replace Abstract: We revisit the standard perturbation-based approach of Abernethy et al.
arXiv Machine Learning
Jun 19
Adversarial Bandit Optimization with Globally Bounded Perturbations to Convex Losses
arXiv:2606. 19891v1 Announce Type: new Abstract: We study adversarial bandit optimization in which the loss functions may be non-convex and non-smooth.
arXiv Machine Learning
Jun 3
From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization
arXiv:2606. 02948v1 Announce Type: new Abstract: Curvature adaptivity is a classical theme in online optimization: for convex Lipschitz losses, adaptive methods interpolate between the optimal $O(\sqrt{T})$ regret for general convex losses and $O(\log T)$ regret under strong convexity.
arXiv Machine Learning
1d ago
Toward Optimal Second-Order Path-Length Guarantee for Adversarial Multi-Armed Bandits
arXiv:2608. 15996v1 Announce Type: new Abstract: We study second-order path-length regret in adversarial $K$-armed bandits against oblivious loss sequences.
arXiv Machine Learning
Jun 3
Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
arXiv:2602. 01903v2 Announce Type: replace Abstract: This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent regret bounds in the stochastic regime.