Optimal Learners for Realizable Regression: PAC Learning and Online Learning

• URL: http://arxiv.org/abs/2307.03848v3
• Date: Wed, 02 Oct 2024 19:31:03 GMT
• Title: Optimal Learners for Realizable Regression: PAC Learning and Online Learning
• Authors: Idan Attias, Steve Hanneke, Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas,
• Abstract summary: We aim to characterize the statistical complexity of realizable regression both in the PAC learning setting and the online learning setting. We first introduce a minimax instance optimal learner for realizable regression and propose a novel dimension that both qualitatively and quantitatively characterizes which classes of real-valued predictors are learnable. In the context of online learning we provide a dimension that characterizes the minimax optimal instance optimal cumulative loss up to a constant factor and design an optimal online learner for realizable regression.
• Score: 52.37726841759983
• License:
• Abstract: In this work, we aim to characterize the statistical complexity of realizable regression both in the PAC learning setting and the online learning setting. Previous work had established the sufficiency of finiteness of the fat shattering dimension for PAC learnability and the necessity of finiteness of the scaled Natarajan dimension, but little progress had been made towards a more complete characterization since the work of Simon (SICOMP '97). To this end, we first introduce a minimax instance optimal learner for realizable regression and propose a novel dimension that both qualitatively and quantitatively characterizes which classes of real-valued predictors are learnable. We then identify a combinatorial dimension related to the Graph dimension that characterizes ERM learnability in the realizable setting. Finally, we establish a necessary condition for learnability based on a combinatorial dimension related to the DS dimension, and conjecture that it may also be sufficient in this context. Additionally, in the context of online learning we provide a dimension that characterizes the minimax instance optimal cumulative loss up to a constant factor and design an optimal online learner for realizable regression, thus resolving an open question raised by Daskalakis and Golowich in STOC '22.

Related papers

• A Combinatorial Characterization of Supervised Online Learnability [20.291598040396302]
  We study the online learnability of hypothesis classes with respect to arbitrary, but bounded loss functions. We give a new scale-sensitive dimension, named the sequential minimax dimension, and show that it gives a tight quantitative characterization of online learnability.
  arXiv  Detail & Related papers  (2023-07-07T20:11:07Z)
• Towards a Better Theoretical Understanding of Independent Subnetwork Training [56.24689348875711]
  We take a closer theoretical look at Independent Subnetwork Training (IST) IST is a recently proposed and highly effective technique for solving the aforementioned problems. We identify fundamental differences between IST and alternative approaches, such as distributed methods with compressed communication.
  arXiv  Detail & Related papers  (2023-06-28T18:14:22Z)
• Learning Capacity: A Measure of the Effective Dimensionality of a Model [18.48866194756127]
  We study a quantity called learning capacity'' which is a measure of the effective dimensionality of a model. We show that the learning capacity is a useful notion of the complexity because (a) it correlates well with the test loss and it is a tiny fraction of the number of parameters for many deep networks trained on typical datasets.
  arXiv  Detail & Related papers  (2023-05-27T02:27:27Z)
• Learnability, Sample Complexity, and Hypothesis Class Complexity for Regression Models [10.66048003460524]
  This work is inspired by the foundation of PAC and is motivated by the existing regression learning issues. The proposed approach, denoted by epsilon-Confidence Approximately Correct (epsilon CoAC), utilizes Kullback Leibler divergence (relative entropy) It enables the learner to compare hypothesis classes of different complexity orders and choose among them the optimum with the minimum epsilon.
  arXiv  Detail & Related papers  (2023-03-28T15:59:12Z)
• Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient [65.08966446962845]
  offline reinforcement learning, which aims at optimizing decision-making strategies with historical data, has been extensively applied in real-life applications. We take a step by considering offline reinforcement learning with differentiable function class approximation (DFA) Most importantly, we show offline differentiable function approximation is provably efficient by analyzing the pessimistic fitted Q-learning algorithm.
  arXiv  Detail & Related papers  (2022-10-03T07:59:42Z)
• Annealing Optimization for Progressive Learning with Stochastic Approximation [0.0]
  We introduce a learning model designed to meet the needs of applications in which computational resources are limited. We develop an online prototype-based learning algorithm that is formulated as an online-free gradient approximation algorithm. The learning model can be viewed as an interpretable and progressively growing competitive neural network model to be used for supervised, unsupervised, and reinforcement learning.
  arXiv  Detail & Related papers  (2022-09-06T21:31:01Z)
• 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)
• Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism [65.46524775457928]
  offline reinforcement learning seeks to utilize offline/historical data to optimize sequential decision-making strategies. We study the statistical limits of offline reinforcement learning with linear model representations.
  arXiv  Detail & Related papers  (2022-03-11T09:00:12Z)
• Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity [51.476337785345436]
  We study a pessimistic variant of Q-learning in the context of finite-horizon Markov decision processes. A variance-reduced pessimistic Q-learning algorithm is proposed to achieve near-optimal sample complexity.
  arXiv  Detail & Related papers  (2022-02-28T15:39:36Z)
• Towards a combinatorial characterization of bounded memory learning [21.031088723668486]
  We develop dimensions that characterize bounded memory learning. We prove both upper and lower bounds for our candidate solution. We conjecture that our characterization holds in a much wider regime of parameters.
  arXiv  Detail & Related papers  (2020-02-08T09:04:21Z)

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.