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

91181272362 · Jun 202019922001200920172026
48 results for strongly adaptive regret

New online conformal prediction methods minimize strongly adaptive regret and achieve near-optimal coverage.

problem Uncertainty quantification in online settings with changing data distributions.
method Developed new online conformal prediction methods that minimize strongly adaptive regret.
result Achieve near-optimal strongly adaptive regret and approximately valid coverage.

SA algorithms control dynamic regret in non-stationary settings with strong convexity or exp-concavity.

problem Non-stationary Online Convex Optimization with dynamic regret control.
method Strongly Adaptive (SA) algorithms view dynamic regret as path variation of the comparator sequence.
result SA algorithms achieve ildeO(TVTlogT) ilde O(\sqrt{TV_T} \vee \log T) and ildeO(dTVTdlogT) ilde O(\sqrt{dTV_T} \vee d\log T) dynamic regret for strongly convex and exp-concave losses, respectively.

New algorithms minimize dynamic regret for strongly convex losses.

problem Minimizing dynamic regret for strongly convex losses.
method Developed Strongly Adaptive algorithms exploiting KKT conditions.
result Achieved near optimal dynamic regret of O(d1/3n1/3extTV[u1:n]2/3d)O(d^{1/3} n^{1/3} ext{TV}[u_{1:n}]^{2/3} \vee d).

A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed "meta" algorithms that convert any online learning algorithm to one that is adaptive to changing environments, where the adaptivity is analyzed in a quantity called the strongly-ad…

2017-11-06abs ↗pdf ↗

Adaptive gradient methods have become recently very popular, in particular as they have been shown to be useful in the training of deep neural networks. In this paper we have analyzed RMSProp, originally proposed for the training of deep neural networks, in the context of online convex optimization and show T\sqrt{T}-…

2017-06-17abs ↗pdf ↗

New method achieves both universality and adaptivity in online convex optimization.

problem Achieve optimal regret guarantees without prior knowledge of function curvature.
method Introduces UniGrad, a novel approach that achieves both universality and adaptivity.
result Achieves universal regret guarantees that adapt to gradient variation.

This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least log(T)\sqrt{\log(T)} better, where TT is the time horizon. Empirical results show tha…

2016-10-14abs ↗pdf ↗

Optimal online linear regression in dynamic environments using discounted Vovk-Azoury-Warmuth forecaster.

problem Achieving optimal performance in dynamic online linear regression without prior knowledge.
method Developed a discounted variant of the Vovk-Azoury-Warmuth forecaster to achieve optimal dynamic regret guarantees.
result Achieved dynamic regret of the form $O\left(d\log(T)\vee \sqrt{dP_{T}^γ(\vec{u})T} ight)$, with a learnable discount factor.

Efficient algorithms for online convex optimization with limited switching decisions.

problem Online convex optimization with limited switching decisions.
method Presented computationally efficient algorithms for both general and strongly convex losses.
result Regret bounds of O(T/S)O(T/S) for general convex losses and O~(T/S2)\widetilde O(T/S^2) for strongly convex losses.

We consider the classical problem of sequential resource allocation where a decision maker must repeatedly divide a budget between several resources, each with diminishing returns. This can be recast as a specific stochastic optimization problem where the objective is to maximize the cumulative reward, or equivalently …

2019-02-12abs ↗pdf ↗

New algorithm achieves optimal regret in non-stochastic control, showing stochasticity is not beneficial.

problem Achieving optimal control in non-stochastic systems with adversarial noise.
method Novel online Newton step algorithm adapted to adversarial disturbances, using policy regret bounds.
result Optimal O~(T)\widetilde{\mathcal{O}}(\sqrt{T}) regret achieved in unknown dynamics, poly(logT)\mathrm{poly}(\log T) regret in known dynamics.

The Adam algorithm has become extremely popular for large-scale machine learning. Under convexity condition, it has been proved to enjoy a data-dependant O(T)O(\sqrt{T}) regret bound where TT is the time horizon. However, whether strong convexity can be utilized to further improve the performance remains an open problem…

2019-05-08abs ↗pdf ↗

New algorithms minimize dynamic regret in non-stationary online learning.

problem Universal dynamic regret minimization under exp-concave and smooth losses.
method Strongly Adaptive algorithms with a path variational based on second order differences of the comparator sequence.
result Achieve a dynamic regret of ildeO(d2n1/5Cn2/5d2) ilde O(d^2 n^{1/5} C_n^{2/5} \vee d^2), optimal modulo dependencies.

Paper analyzes regret bounds for unconstrained online optimization.

problem Minimizing regret in dynamic online learning for strongly convex and smooth functions.
method Preconditioned OGD, Online Optimistic Newton (OON), multiple gradient queries.
result Achieves O(C2,T)O(C^*_{2,T}) regret bound with one gradient query per round.

Improved online convex optimization with delayed feedback using curvature.

problem Online convex optimization with curved losses and delayed feedback.
method Variant of follow-the-regularized-leader and Online Newton Step algorithm with adaptive learning rate.
result Regret bounds of order min{σmaxlnT,dtot}\min\{σ_{\max}\ln T, \sqrt{d_{\mathrm{tot}}}\} for exp-concave losses.

New algorithm exploits curvature of feasible sets for fast online convex optimization.

problem Online convex optimization with fast rates.
method Adapting FTL algorithm to curvature of feasible sets.
result Achieves logarithmic regret bound of O(ρlogT)O(ρ\log T) in stochastic environments.

We derive upper and lower bounds for the policy regret of TT-round online learning problems with graph-structured feedback, where the adversary is nonoblivious but assumed to have a bounded memory. We obtain upper bounds of O~(T2/3)\widetilde O(T^{2/3}) and O~(T3/4)\widetilde O(T^{3/4}) for strongly-observable and weakly-observab…

2018-04-01abs ↗pdf ↗

The paper tackles minimax optimality in continuum contextual bandits with Hölder continuity.

problem Minimizing regret in a continuum of contexts with Hölder continuity.
method Proves a static-to-contextual regret conversion theorem and analyzes various dependency cases.
result Achieves minimax optimal contextual regret for convex and strongly convex bandits.

Adaptive designs achieve strong Neyman regret guarantees for ATE estimation.

problem Estimating unbiased average treatment effect in sequential experiments.
method Proposed adaptive designs with O~(logT)\widetilde{O}(\log T) Neyman regret under boundedness assumptions and O~(T)\widetilde{O}(\sqrt{T}) multigroup Neyman regret in covariate-based settings.
result Adaptive designs outperform non-adaptive designs in terms of Neyman regret, especially in covariate-based settings.

New approach for distributed online optimization of non-convex losses with sublinear regret.

problem Regret evaluation and consensus in distributed, multi-agent systems with non-convex losses.
method Composite regret metric and consensus-based online normalized gradient (CONGD) approach for pseudo-convex losses; offline optimization oracle for general non-convex losses.
result First sublinear regret bound for general distributed online non-convex learning.

Regret minimization is treated as the golden rule in the traditional study of online learning. However, regret minimization algorithms tend to converge to the static optimum, thus being suboptimal for changing environments. To address this limitation, new performance measures, including dynamic regret and adaptive regr…

2020-02-06abs ↗pdf ↗

Paper tackles online control of linear systems with unbounded noise.

problem Online control of linear systems under unbounded noise with unknown convex cost functions.
method Developed an algorithm achieving ildeO(T) ilde{O}(\sqrt{T}) high-probability regret under unbounded noise, and established O(mpoly(logT)) O({ m poly} (\log T)) regret bound for strongly convex costs and sub-Gaussian noise.
result Achieved ildeO(T) ilde{O}(\sqrt{T}) high-probability regret under unbounded noise, and O(mpoly(logT)) O({ m poly} (\log T)) regret bound for specific noise and cost conditions.

Optimistic Hedge achieves optimal regret bounds in two-player zero-sum games.

problem Achieving optimal regret bounds for optimistic Hedge in two-player zero-sum games.
method Refined regret analysis and optimization problem formulation.
result Optimistic Hedge achieves O(logmlogn)O(\sqrt{\log m \log n}) regret bounds, matching upper and lower bounds.

We investigate online convex optimization in changing environments, and choose the adaptive regret as the performance measure. The goal is to achieve a small regret over every interval so that the comparator is allowed to change over time. Different from previous works that only utilize the convexity condition, this pa…

2019-04-26abs ↗pdf ↗

New algorithm reduces regret for many bandit algorithms with logarithmic dependence on number of algorithms.

problem Combining and learning over a large set of adversarial bandit algorithms to track the best one.
method Proposes a new algorithm (CORRAL) with logarithmic regret dependence on the number of base algorithms.
result Achieves optimal switching regret for adversarial linear bandits over a dd-dimensional p\ell_p unit-ball.

Improved COCO algorithms with better constraint control.

problem Achieving small regret and constraint violation in online convex optimization.
method Simple projection-based algorithm leveraging self-contraction geometry.
result Exponential improvement in cumulative constraint violation for strongly convex losses.

We propose algorithms for online principal component analysis (PCA) and variance minimization for adaptive settings. Previous literature has focused on upper bounding the static adversarial regret, whose comparator is the optimal fixed action in hindsight. However, static regret is not an appropriate metric when the un…

2019-01-23abs ↗pdf ↗

New algorithms reduce regret for online submodular maximization under various conditions.

problem Online optimization of submodular functions with adversarial or random utilities.
method Characterized strongly DR-submodular functions and derived bounds for different utility classes.
result Logarithmic regret bounds for adversarial strongly DR-submodular functions and submodular functions with random order.

We study optimal regret bounds for control in linear dynamical systems under adversarially changing strongly convex cost functions, given the knowledge of transition dynamics. This includes several well studied and fundamental frameworks such as the Kalman filter and the linear quadratic regulator. State of the art met…

2019-09-11abs ↗pdf ↗

The paper explores trade-offs between regret and variance in online learning algorithms.

problem Investigating the trade-offs between regret and variance in online learning.
method Analysis of the Exponentially Weighted Average (EWA) algorithm and its variants.
result A variant of EWA either achieves negative regret or guarantees a logarithmic bound on both variance and regret.

New adaptive learning rate for FTRL reduces regret to Θ(T^2/3).

problem Minimax regret of Θ(T^2/3) in online learning.
method Adaptive learning rate framework matching stability, penalty, and bias terms.
result Improves Best-of-Both-Worlds (BOBW) regret upper bounds.

Improved algorithm for adaptive dueling bandits with near-optimal regret bound.

problem Non-stationary dueling bandits with unknown number of preference changes.
method Elimination-based rescheduling algorithm for adaptive dynamic regret.
result Near-optimal ildeO(SextttCWT) ilde{O}(\sqrt{S^{ exttt{CW}} T}) dynamic regret bound.