Optimality of Robust Online Learning

• URL: http://arxiv.org/abs/2304.10060v1
• Date: Thu, 20 Apr 2023 03:00:33 GMT
• Title: Optimality of Robust Online Learning
• Authors: Zheng-Chu Guo, Andreas Christmann, Lei Shi
• Abstract summary: We study an online learning algorithm with a robust loss function $mathcalL_sigma$ for regression over a reproducing kernel Hilbert space (RKHS) The proposed algorithm is then a robust alternative for online least squares regression aiming to estimate the conditional mean function.
• Score: 4.21768682940933
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we study an online learning algorithm with a robust loss function $\mathcal{L}_{\sigma}$ for regression over a reproducing kernel Hilbert space (RKHS). The loss function $\mathcal{L}_{\sigma}$ involving a scaling parameter $\sigma>0$ can cover a wide range of commonly used robust losses. The proposed algorithm is then a robust alternative for online least squares regression aiming to estimate the conditional mean function. For properly chosen $\sigma$ and step size, we show that the last iterate of this online algorithm can achieve optimal capacity independent convergence in the mean square distance. Moreover, if additional information on the underlying function space is known, we also establish optimal capacity dependent rates for strong convergence in RKHS. To the best of our knowledge, both of the two results are new to the existing literature of online learning.

Related papers

• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path [80.60592344361073]
  We study the Shortest Path (SSP) problem with a linear mixture transition kernel. An agent repeatedly interacts with a environment and seeks to reach certain goal state while minimizing the cumulative cost. Existing works often assume a strictly positive lower bound of the iteration cost function or an upper bound of the expected length for the optimal policy.
  arXiv  Detail & Related papers  (2024-02-14T07:52:00Z)
• Convergence analysis of online algorithms for vector-valued kernel regression [0.42970700836450487]
  We consider the problem of approximating the regression function from noisy vector-valued data by an online learning algorithm. We show that the expected squared error in the RKHS norm can be bounded by $C2 (m+1)-s/(2+s)$, where $m$ is the current number of processed data.
  arXiv  Detail & Related papers  (2023-09-14T15:10:47Z)
• Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach [57.92727189589498]
  We propose an online convex optimization approach with two different levels of adaptivity. We obtain $mathcalO(log V_T)$, $mathcalO(d log V_T)$ and $hatmathcalO(sqrtV_T)$ regret bounds for strongly convex, exp-concave and convex loss functions.
  arXiv  Detail & Related papers  (2023-07-17T09:55:35Z)
• Refined Regret for Adversarial MDPs with Linear Function Approximation [50.00022394876222]
  We consider learning in an adversarial Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes. This paper provides two algorithms that improve the regret to $tildemathcal O(K2/3)$ in the same setting.
  arXiv  Detail & Related papers  (2023-01-30T14:37:21Z)
• Randomized Exploration for Reinforcement Learning with General Value Function Approximation [122.70803181751135]
  We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm. Our algorithm drives exploration by simply perturbing the training data with judiciously chosen i.i.d. scalar noises. We complement the theory with an empirical evaluation across known difficult exploration tasks.
  arXiv  Detail & Related papers  (2021-06-15T02:23:07Z)
• Efficient Online-Bandit Strategies for Minimax Learning Problems [21.300877551771197]
  Several learning problems involve solving min-max problems, e.g., empirical distributional robust learning or minimization with non-standard aggregated losses. More specifically, these problems are convex-linear problems where the learning is carried out over the model parameters $winmathcalW$ and over the empirical distribution $pinmathcalK$ of the training set. To design efficient methods, we let an online learning algorithm play against a (combinatorial) bandit algorithm.
  arXiv  Detail & Related papers  (2021-05-28T16:01:42Z)
• An $L^2$ Analysis of Reinforcement Learning in High Dimensions with Kernel and Neural Network Approximation [9.088303226909277]
  This paper considers the situation where the function approximation is made using the kernel method or the two-layer neural network model. We establish an $tildeO(H3|mathcal A|frac14n-frac14)$ bound for the optimal policy with $Hn$ samples. Even though this result still requires a finite-sized action space, the error bound is independent of the dimensionality of the state space.
  arXiv  Detail & Related papers  (2021-04-15T21:59:03Z)
• Online Model Selection for Reinforcement Learning with Function Approximation [50.008542459050155]
  We present a meta-algorithm that adapts to the optimal complexity with $tildeO(L5/6 T2/3)$ regret. We also show that the meta-algorithm automatically admits significantly improved instance-dependent regret bounds.
  arXiv  Detail & Related papers  (2020-11-19T10:00:54Z)
• Statistical-Query Lower Bounds via Functional Gradients [19.5924910463796]
  We show that any statistical-query algorithm with tolerance $n- (1/epsilon)b$ must use at least $2nc epsilon$ queries for some constant $b. Our results rule out general (as opposed to correlational) SQ learning algorithms, which is unusual for real-valued learning problems.
  arXiv  Detail & Related papers  (2020-06-29T05:15:32Z)

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.