Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

234469703937 · Jun 202019922001200920172026
48 results for bandit online convex optimization

Unified framework for analyzing online convex optimization across various settings.

problem Analyzing online convex optimization in different settings and feedback types.
method Unified framework allowing systematic proposal and analysis of meta-algorithms.
result Comparable regret bounds for various feedback types and adversary types.

Study on collaborative vs. non-collaborative online and bandit convex optimization.

problem Minimizing average regret in distributed online and bandit convex optimization.
method Analyzes the impact of collaboration in adaptive and zeroth-order feedback settings.
result Collaboration is beneficial in high-dimensional federated online optimization with limited feedback.

Improved online learning for hidden-convex losses achieves optimal regret.

problem Adversarial online learning with nonconvex losses that become convex after reparameterization.
method Algorithmic equivalence between OGD and OMD on convex losses, with Hessian compatibility condition.
result OGD achieves O(T)\mathcal{O}(\sqrt{T}) regret for hidden-convex losses, matching optimal rate.

Motivated by applications in clinical trials and finance, we study the problem of online convex optimization (with bandit feedback) where the decision maker is risk-averse. We provide two algorithms to solve this problem. The first one is a descent-type algorithm which is easy to implement. The second algorithm, which …

2018-10-01abs ↗pdf ↗

SCaLE tackles dynamic regret in noisy bandit feedback with switching costs.

problem Unbounded metric movement costs in bandit online convex optimization.
method SCaLE algorithm for high-dimensional dynamic quadratic hitting costs and 2\ell_2-norm switching costs, with spectral regret analysis.
result First algorithm achieving sub-linear dynamic regret without hitting cost knowledge.

New method tackles online DR-submodular maximization with improved regret guarantees.

problem Online maximization of non-monotone DR-submodular functions over down-closed convex sets.
method 1/e-linearization through exponential reparametrization, surrogate potential, and reduction to online linear optimization.
result Achieves O(T1/2)O(T^{1/2}) static regret with single gradient query per round, improving state of the art.

Paper addresses private online convex optimization with optimal algorithms in various geometries and high-dimensional bandits.

problem Private online convex optimization with streaming and continual release data.
method Proposes a private variant of online Frank-Wolfe algorithm with recursive gradients for variance reduction.
result Achieves optimal excess risk in linear time for 1<p21<p\leq 2 and state-of-the-art excess risk for 2<p2<p\leq\infty.

We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds are not improvable in general. The basic idea utilizes tools from con…

2011-10-19abs ↗pdf ↗

New algorithms robust to adversarial data achieve optimal performance.

problem Adversarial robustness in high-dimensional online learning problems.
method Alternating minimization scheme combining least-squares and convex reweighting.
result Achieves optimal robustness guarantees without distributional assumptions.

Study tackles non-stationary bandit convex optimization with new algorithms.

problem Minimizing regret in non-stationary environments with various measures of non-stationarity.
method Proposed Tilted Exponentially Weighted Average with Sleeping Experts (TEWA-SE) for strongly convex losses and clipped Exploration by Optimization (cExO) for general convex losses.
result Proved minimax-optimality of TEWA-SE for strongly convex losses and introduced cExO for general convex losses.

Paper introduces a new GG^\star regret measure for online convex optimization with smooth losses.

problem Online convex optimization with smooth losses.
method Introduces a new GG^\star regret measure that depends on the cumulative squared gradient norm.
result The GG^\star regret can be arbitrarily sharper than existing measures when losses have vanishing curvature.

We consider dynamic pricing with many products under an evolving but low-dimensional demand model. Assuming the temporal variation in cross-elasticities exhibits low-rank structure based on fixed (latent) features of the products, we show that the revenue maximization problem reduces to an online bandit convex optimiza…

2018-01-30abs ↗pdf ↗

Stochastic multi-armed bandits form a class of online learning problems that have important applications in online recommendation systems, adaptive medical treatment, and many others. Even though potential attacks against these learning algorithms may hijack their behavior, causing catastrophic loss in real-world appli…

2019-05-16abs ↗pdf ↗

Unified meta-algorithm improves average performance across similar tasks in adversarial bandits.

problem Improving performance across multiple similar tasks in adversarial bandit settings.
method Unified meta-algorithm for multi-armed bandits and bandit linear optimization, tuning initialization, step-size, and entropy parameters.
result Unified meta-algorithm yields setting-specific guarantees for MAB and BLO, improving task-averaged regret.

In this paper we develop the first algorithms for online submodular minimization that preserve differential privacy under full information feedback and bandit feedback. A sequence of TT submodular functions over a collection of nn elements arrive online, and at each timestep the algorithm must choose a subset of $[n]…

2018-07-06abs ↗pdf ↗

In this book, I introduce the concepts of online learning through a modern view based on convex optimization. Here, online learning refers to the framework of regret minimization under worst-case assumptions. I attempted to unify all the literature as instantiations of Online Mirror Descent and Follow-the-Regularized-L…

2019-12-31abs ↗pdf ↗

We consider the problem of bandit optimization, inspired by stochastic optimization and online learning problems with bandit feedback. In this problem, the objective is to minimize a global loss function of all the actions, not necessarily a cumulative loss. This framework allows us to study a very general class of pro…

2017-02-22abs ↗pdf ↗

Transforms offline greedy algorithms to online algorithms for combinatorial problems.

problem Online decision-making in time-varying combinatorial environments.
method General framework using Blackwell approachability and Bandit Blackwell approachability.
result Achieves O(T)O(\sqrt{T}) regret in full information setting and O(T2/3)O(T^{2/3}) regret in bandit setting.

We revisit the challenge of designing online algorithms for the bandit convex optimization problem (BCO) which are also scalable to high dimensional problems. Hence, we consider algorithms that are \textit{projection-free}, i.e., based on the conditional gradient method whose only access to the feasible decision set, i…

2019-10-08abs ↗pdf ↗

Improved online convex optimization bounds between stochastic and adversarial settings.

problem Understanding optimization tasks that are neither i.i.d. nor fully adversarial.
method Establishing novel regret bounds exploiting smoothness of expected losses.
result Regret bounds improve on previous results by reducing dependence on maximum gradient length to variance of gradients.

Meta-learning improves performance across similar tasks in adversarial bandit settings.

problem Improving performance across multiple similar tasks in adversarial bandit scenarios.
method Designing meta-algorithms that combine outer learners to tune hyperparameters of inner learners for MAB and BLO.
result Meta-algorithms improve task-averaged regret for MAB and BLO, showing direct relationship with action space-dependent measures.

Algorithm identifies best arm in combinatorial bandits with semi-bandit feedback.

problem Identifying the best arm in combinatorial bandits with semi-bandit feedback.
method Interpreted as a sequential zero-sum game, developed a CombGame meta-algorithm with finite time guarantees.
result First computationally efficient algorithm that is asymptotically optimal and has competitive empirical performance.

Algorithms for bandit convex optimization and online learning often rely on constructing noisy gradient estimates, which are then used in appropriately adjusted first-order algorithms, replacing actual gradients. Depending on the properties of the function to be optimized and the nature of ``noise'' in the bandit feedb…

2016-09-22abs ↗pdf ↗

Efficient strategies for online learning against bandit algorithms solve minimax problems.

problem Solving min-max problems in convex-linear settings with empirical distributions.
method Designing online learning algorithms that play against bandit algorithms, leveraging properties of the set of empirical distributions.
result High-probability convergence guarantees to minimax values for a specific family of sets.

We use online convex optimization (OCO) for setpoint tracking with uncertain, flexible loads. We consider full feedback from the loads, bandit feedback, and two intermediate types of feedback: partial bandit where a subset of the loads are individually observed and the rest are observed in aggregate, and Bernoulli feed…

2017-09-12abs ↗pdf ↗

New bounds for online convex optimization between stochastic and adversarial settings.

problem Understanding optimization tasks that are neither i.i.d. nor fully adversarial.
method Establishing novel regret bounds exploiting smoothness of expected losses.
result Regret bounds match expected rates in the fully i.i.d. case and gracefully deteriorate in the fully adversarial case.

PyXAB is a Python library for X-armed bandits and online optimization.

problem Efficiently solving X-armed bandit problems and online blackbox optimization.
method Implementation of 10+ X-armed bandit algorithms and synthetic objectives.
result Evaluation of different algorithms' performance on various synthetic objectives.

Paper tackles stochastic kk-submodular bandits with full feedback, achieving sublinear regret.

problem Online optimization of kk-submodular functions with full-bandit feedback.
method Proposes online algorithms for various kk-submodular stochastic combinatorial multi-armed bandit problems.
result Achieves sublinear αα-regret bounds for multiple kk-submodular stochastic combinatorial multi-armed bandit problems.

Optimistic algorithm reduces regret and constraint violations in online convex optimization with adversarial constraints.

problem Online convex optimization with adversarial constraints.
method Improved algorithm using accurate predictions of loss and constraint functions.
result Improved bounds on regret and cumulative constraint violations.

This article introduces the concepts around Online Bandit Linear Optimization and explores an efficient setup called SCRiBLe (Self-Concordant Regularization in Bandit Learning) created by Abernethy et. al.\cite{abernethy}. The SCRiBLe setup and algorithm yield a O(T)O(\sqrt{T}) regret bound and polynomial run time comple…

2018-05-11abs ↗pdf ↗