New Projection-free Algorithms for Online Convex Optimization with Adaptive Regret Guarantees

• URL: http://arxiv.org/abs/2202.04721v3
• Date: Sun, 19 Mar 2023 10:11:15 GMT
• Title: New Projection-free Algorithms for Online Convex Optimization with Adaptive Regret Guarantees
• Authors: Dan Garber, Ben Kretzu
• Abstract summary: We present new efficient textitprojection-free algorithms for online convex optimization (OCO) Our algorithms are based on the textitonline gradient descent algorithm with a novel and efficient approach to computing so-called textitinfeasible projections We present algorithms which, using overall $O(T)$ calls to the separation oracle, guarantee $O(sqrtT)$ adaptive regret and $O(T3/4)$ adaptive expected regret.
• Score: 21.30065439295409
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present new efficient \textit{projection-free} algorithms for online convex optimization (OCO), where by projection-free we refer to algorithms that avoid computing orthogonal projections onto the feasible set, and instead relay on different and potentially much more efficient oracles. While most state-of-the-art projection-free algorithms are based on the \textit{follow-the-leader} framework, our algorithms are fundamentally different and are based on the \textit{online gradient descent} algorithm with a novel and efficient approach to computing so-called \textit{infeasible projections}. As a consequence, we obtain the first projection-free algorithms which naturally yield \textit{adaptive regret} guarantees, i.e., regret bounds that hold w.r.t. any sub-interval of the sequence. Concretely, when assuming the availability of a linear optimization oracle (LOO) for the feasible set, on a sequence of length $T$, our algorithms guarantee $O(T^{3/4})$ adaptive regret and $O(T^{3/4})$ adaptive expected regret, for the full-information and bandit settings, respectively, using only $O(T)$ calls to the LOO. These bounds match the current state-of-the-art regret bounds for LOO-based projection-free OCO, which are \textit{not adaptive}. We also consider a new natural setting in which the feasible set is accessible through a separation oracle. We present algorithms which, using overall $O(T)$ calls to the separation oracle, guarantee $O(\sqrt{T})$ adaptive regret and $O(T^{3/4})$ adaptive expected regret for the full-information and bandit settings, respectively.

Related papers

• Online Convex Optimization with a Separation Oracle [10.225358400539719]
  We introduce a new projection-free algorithm for Online Convex Optimization (OCO) with a state-of-the-art regret guarantee. Our algorithm achieves a regret bound of $widetildeO(sqrtdT + kappa d)$, while requiring only $widetildeO(1) calls to a separation oracle per round.
  arXiv  Detail & Related papers  (2024-10-03T13:35:08Z)
• Perturb-and-Project: Differentially Private Similarities and Marginals [73.98880839337873]
  We revisit the input perturbations framework for differential privacy where noise is added to the input $Ain mathcalS$. We first design novel efficient algorithms to privately release pair-wise cosine similarities. We derive a novel algorithm to compute $k$-way marginal queries over $n$ features.
  arXiv  Detail & Related papers  (2024-06-07T12:07:16Z)
• 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)
• Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds [27.92755687977196]
  The paper proposes a linear bandit algorithm that is adaptive to environments at two different levels of hierarchy. At the higher level, the proposed algorithm adapts to a variety of types of environments. The proposed algorithm has data-dependent regret bounds that depend on all of the cumulative loss for the optimal action.
  arXiv  Detail & Related papers  (2023-02-24T00:02:24Z)
• Deterministic Nonsmooth Nonconvex Optimization [94.01526844386977]
  We show that randomization is necessary to obtain a dimension-free dimension-free algorithm. Our algorithm yields the first deterministic dimension-free algorithm for optimizing ReLU networks.
  arXiv  Detail & Related papers  (2023-02-16T13:57:19Z)
• Projection-free Online Exp-concave Optimization [21.30065439295409]
  We present an LOO-based ONS-style algorithm, which using overall $O(T)$ calls to a LOO, guarantees in worst case regret bounded by $widetildeO(n2/3T2/3)$. Our algorithm is most interesting in an important and plausible low-dimensional data scenario.
  arXiv  Detail & Related papers  (2023-02-09T18:58:05Z)
• Accelerated First-Order Optimization under Nonlinear Constraints [73.2273449996098]
  We exploit between first-order algorithms for constrained optimization and non-smooth systems to design a new class of accelerated first-order algorithms. An important property of these algorithms is that constraints are expressed in terms of velocities instead of sparse variables.
  arXiv  Detail & Related papers  (2023-02-01T08:50:48Z)
• Projection-free Adaptive Regret with Membership Oracles [31.422532403048738]
  Most iterative algorithms require the computation of projections onto convex sets, which can be computationally expensive. Recent work by GK22 gave sublinear adaptive regret guarantees with projection free algorithms based on the Frank Wolfe approach. We give projection-free algorithms that are based on a different technique, inspired by Mhammedi22, that replaces projections by set-membership computations.
  arXiv  Detail & Related papers  (2022-11-22T23:53:06Z)
• Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability [59.81339109121384]
  We study the $K$ contextual dueling bandit problem, a sequential decision making setting in which the learner uses contextual information to make two decisions, but only observes emphpreference-based feedback suggesting that one decision was better than the other. We provide a new algorithm that achieves the optimal regret rate for a new notion of best response regret, which is a strictly stronger performance measure than those considered in prior works.
  arXiv  Detail & Related papers  (2021-11-24T07:14:57Z)
• Adapting to Misspecification in Contextual Bandits [82.55565343668246]
  We introduce a new family of oracle-efficient algorithms for $varepsilon$-misspecified contextual bandits. We obtain the first algorithm that achieves the optimal $O(dsqrtT + varepsilonsqrtdT)$ regret bound for unknown misspecification level.
  arXiv  Detail & Related papers  (2021-07-12T21:30:41Z)
• Conservative Stochastic Optimization with Expectation Constraints [11.393603788068777]
  This paper considers convex optimization problems where the objective and constraint functions involve expectations with respect to the data indices or environmental variables. Online and efficient approaches for solving such problems have not been widely studied. We propose a novel conservative optimization algorithm (CSOA) that achieves zero constraint violation and $Oleft(T-frac12right)$ optimality gap.
  arXiv  Detail & Related papers  (2020-08-13T08:56:24Z)

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.