Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective

• URL: http://arxiv.org/abs/2502.10292v1
• Date: Fri, 14 Feb 2025 16:52:50 GMT
• Title: Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective
• Authors: Adam Block, Abhishek Shetty,
• Abstract summary: We present an oracle-efficient algorithm capable of achieving small-loss bounds with improved rates in greater generality than previous work. We also present a variant for differentially private learning that attains optimal rates, again under our separation condition.
• Score: 9.867914513513453
• License:
• Abstract: In order to develop practical and efficient algorithms while circumventing overly pessimistic computational lower bounds, recent work has been interested in developing oracle-efficient algorithms in a variety of learning settings. Two such settings of particular interest are online and differentially private learning. While seemingly different, these two fields are fundamentally connected by the requirement that successful algorithms in each case satisfy stability guarantees; in particular, recent work has demonstrated that algorithms for online learning whose performance adapts to beneficial problem instances, attaining the so-called small-loss bounds, require a form of stability similar to that of differential privacy. In this work, we identify the crucial role that separation plays in allowing oracle-efficient algorithms to achieve this strong stability. Our notion, which we term $\rho$-separation, generalizes and unifies several previous approaches to enforcing this strong stability, including the existence of small-separator sets and the recent notion of $\gamma$-approximability. We present an oracle-efficient algorithm that is capable of achieving small-loss bounds with improved rates in greater generality than previous work, as well as a variant for differentially private learning that attains optimal rates, again under our separation condition. In so doing, we prove a new stability result for minimizers of a Gaussian process that strengthens and generalizes previous work.

Related papers

• Optimization by Parallel Quasi-Quantum Annealing with Gradient-Based Sampling [0.0]
  This study proposes a different approach that integrates gradient-based update through continuous relaxation, combined with Quasi-Quantum Annealing (QQA) Numerical experiments demonstrate that our method is a competitive general-purpose solver, achieving performance comparable to iSCO and learning-based solvers.
  arXiv  Detail & Related papers  (2024-09-02T12:55:27Z)
• Overcoming Brittleness in Pareto-Optimal Learning-Augmented Algorithms [6.131022957085439]
  We propose a new framework in which the smoothness in the performance of the algorithm is enforced by means of a user-specified profile. We apply this new approach to a well-studied online problem, namely the one-way trading problem.
  arXiv  Detail & Related papers  (2024-08-07T23:15:21Z)
• Optimal Algorithms for Stochastic Complementary Composite Minimization [55.26935605535377]
  Inspired by regularization techniques in statistics and machine learning, we study complementary composite minimization. We provide novel excess risk bounds, both in expectation and with high probability. Our algorithms are nearly optimal, which we prove via novel lower complexity bounds for this class of problems.
  arXiv  Detail & Related papers  (2022-11-03T12:40:24Z)
• Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning [53.17258888552998]
  This work proposes an exploration variant of the basic $Q$-learning protocol with linear function approximation. We show that the performance of the algorithm degrades very gracefully under a novel and more permissive notion of approximation error.
  arXiv  Detail & Related papers  (2022-06-01T23:26:51Z)
• Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise Learning [65.54757265434465]
  Pairwise learning refers to learning tasks where the loss function depends on a pair instances. Online descent (OGD) is a popular approach to handle streaming data in pairwise learning. In this paper, we propose simple and online descent to methods for pairwise learning.
  arXiv  Detail & Related papers  (2021-11-23T18:10:48Z)
• A Boosting Approach to Reinforcement Learning [59.46285581748018]
  We study efficient algorithms for reinforcement learning in decision processes whose complexity is independent of the number of states. We give an efficient algorithm that is capable of improving the accuracy of such weak learning methods.
  arXiv  Detail & Related papers  (2021-08-22T16:00:45Z)
• Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation [92.3161051419884]
  We study reinforcement learning with linear function approximation. Existing algorithms only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees. We propose a new algorithm called FLUTE, which enjoys uniform-PAC convergence to the optimal policy with high probability.
  arXiv  Detail & Related papers  (2021-06-22T08:48:56Z)
• Machine Unlearning via Algorithmic Stability [31.809738694273623]
  We study the problem of machine unlearning and identify a notion of Total Variation (TV) stability. For convex risk minimization problems, we design TV-stable algorithms based on noisy Gradient Descent (SGD) Our techniques to generalize our algorithms are differentially private as well.
  arXiv  Detail & Related papers  (2021-02-25T21:16:56Z)
• An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits [129.1029690825929]
  We introduce a novel algorithm improving over the state-of-the-art along multiple dimensions. We establish minimax optimality for any learning horizon in the special case of non-contextual linear bandits.
  arXiv  Detail & Related papers  (2020-10-23T09:12:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.