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.

168,657 papers · 148 categories

Trend · papers per month

169337506674 · Jun 202019922001200920172026
48 results for linear regret bound

Improved regret bound for linear ensemble sampling.

problem Closing the gap between theory and practice in linear ensemble sampling.
method General regret analysis framework for linear bandit algorithms, revealing a relationship with LinPHE.
result Achieves a frequentist regret bound of ildeO(d3/2T) ilde{O}(d^{3/2}\sqrt{T}) for linear ensemble sampling.

We establish linear regret bounds for convex smooth losses using Fenchel-Young losses.

problem Establishing linear regret bounds for convex smooth losses.
method Constructing a convex smooth surrogate loss using Fenchel-Young losses generated by the convolutional negentropy.
result We derive a smooth loss with a linear surrogate regret bound.

A new linear contextual bandit algorithm with improved regret bound.

problem Efficiently solving linear contextual bandit problems with reduced regret.
method Proposes a novel estimator embedded with exploration and a self-normalized bound.
result Regret bound matches lower bound of Ω(dT)Ω(\sqrt{dT}) up to logarithmic factors.

This paper achieves optimal regret bounds for locally private linear contextual bandit.

problem Designing locally private linear contextual bandit algorithms with optimal regret bounds.
method New algorithmic and analytical ideas, including mean absolute deviation analysis and layered principal component regression.
result Achieves an ildeO(T) ilde O(\sqrt{T}) regret upper bound for locally private linear contextual bandit.

Bayesian bandit algorithms with approximate inference improve regret bounds in stochastic linear bandits.

problem Theoretical justification for Bayesian bandit algorithms with approximate inference in stochastic linear bandits.
method Proposed a theoretical framework to analyze approximate inference impact and conducted frequentist regret analysis on LinTS and LinBUCB.
result LinTS and LinBUCB preserve their original regret upper bounds with larger constant terms in approximate inference settings.

The paper addresses frequentist regret of Linear Thompson Sampling in stochastic linear bandits.

problem The frequentist regret of Linear Thompson Sampling (LinTS) is worse than its Bayesian counterpart.
method The paper proves the fundamental nature of the frequentist regret bound for LinTS and proposes a data-driven version of LinTS to achieve minimax optimal frequentist regret.
result The frequentist regret bound for LinTS is O~(ddT)\widetilde{\mathcal{O}}(d\sqrt{dT}), which is the best possible under certain conditions.

New algorithms for linear bandits avoid norm knowledge, reducing regret.

problem Linear bandits require knowledge of norm bound SS on parameter θθ^*, leading to high regret.
method Proposes two novel algorithms for changing and fixed arm sets, analyzing their regret bounds.
result Regret bounds show no significant price for not knowing SS, with no price for fixed arm sets.

Logarithmic regret achieved in RL with linear function approximation.

problem Achieving logarithmic regret in reinforcement learning with linear function approximation.
method LSVI-UCB for linear MDP assumption, UCRL-VTR for linear mixture MDP assumption.
result Logarithmic regret bounds established for RL with linear function approximation.

Balances and eliminates base algorithms in bandits and RL to bound total regret.

problem Model selection in bandits and reinforcement learning with unknown optimal regret.
method Balances and eliminates base algorithms based on candidate regret bounds.
result Total regret bound is the best valid candidate regret bound times a small multiplicative factor.

This paper improves online learning algorithms for LP problems, achieving better regret bounds.

problem Achieving optimal regret bounds in online linear programming.
method Develops a new framework for first-order online learning algorithms under certain error bound conditions.
result First-order learning algorithms achieve o(T)o(\sqrt{T}) regret in continuous support and O(logT)\mathcal{O}(\log T) regret in finite support, improving over O(T)\mathcal{O}(\sqrt{T}).

New algorithm reduces regret in linear mixture SSPs without cost bounds.

problem Learning optimal paths in stochastic environments with cost constraints.
method Extended value iteration with variance-aware confidence set.
result Achieves nearly minimax optimal regret bound of O(dBK)O(dB_*\sqrt{K}).

New bounds for high-dimensional sparse linear bandits, balancing information and regret.

problem Stochastic linear bandits with high-dimensional sparse features.
method Derivation of minimax regret lower and upper bounds for explore-then-commit algorithm.
result Optimal rate of Θ(n2/3)Θ(n^{2/3}) for data-poor regime, complemented by O(n)O(\sqrt{n}) under signal magnitude assumption.

New bounds on self-normalized martingales improve online linear regression performance.

problem Improving regret bounds in online linear regression.
method Characterizing scale-invariant bounds on self-normalized martingales.
result For d=1d=1, O(logT)O(\log T) doubly-uniform regret is possible; for d>1d>1, sublinear doubly-uniform regret is impossible.

An algorithm for maximizing rewards under linear cost constraints.

problem Maximizing rewards while adhering to cost constraints in a linear bandit problem.
method Proposes an upper-confidence bound algorithm called optimistic pessimistic linear bandit (OPLB) for constrained contextual linear bandits.
result Proves an O~(dTτc0)\widetilde{\mathcal{O}}(\frac{d\sqrt{T}}{τ-c_0}) bound on regret for the proposed algorithm.

New algorithm learns optimal path in reinforcement learning with linear approximations.

problem Optimal path learning in reinforcement learning with linear approximations.
method Proposes novel algorithm with Hoeffding-type and Bernstein-type confidence sets.
result Achieves near-optimal regret guarantee for linear mixture SSP.

IDS improves sparse linear bandits by balancing information and regret.

problem Sparse linear bandits in high-dimensional decision-making.
method Information-directed sampling (IDS) with Bayesian regret bounds and empirical Bayesian sparse posterior sampling.
result IDS nearly matches existing lower bounds and significantly reduces regret.

Randomized exploration in linear bandits achieves optimal regret bounds.

problem Optimizing exploration in high-dimensional linear bandit problems.
method Analysis of Thompson sampling without forced optimism.
result Randomized exploration algorithms achieve an O(dnlog(n))O(d\sqrt{n} \log(n)) regret bound in smooth, strongly convex action spaces.

Significant improvements in regret analysis for adaptive online learning problems.

problem Exploiting low variance in online learning problems without known variances.
method Novel peeling-based regret analysis leveraging elliptical potential `count` lemma.
result Significant improvements in regret bounds for linear bandits and linear mixture MDPs.

TRAiL is a linear bandit algorithm that ensures optimal regret and guarantees inference quality.

problem Optimal regret and inference quality in linear bandits with convex action sets.
method TRAiL estimates the parameter through regularized least squares and perturbs the action set along the tangent plane.
result TRAiL achieves an Ω(T)Ω(\sqrt{T}) upper bound on cumulative regret with high probability.

New method for linear bandits with unknown sparsity, improving sparse regret bounds.

problem Sparse regret bounds for unknown sparsity and adversarial action sets.
method Combines online to confidence set conversions with randomized model selection over nested confidence sets.
result First sparse regret bounds for unknown sparsity and adversarial action sets.

We study the problem of regret minimization in partially observable linear quadratic control systems when the model dynamics are unknown a priori. We propose ExpCommit, an explore-then-commit algorithm that learns the model Markov parameters and then follows the principle of optimism in the face of uncertainty to desig…

2020-01-31abs ↗pdf ↗

New algorithm reduces regret in CBs with time-varying models.

problem Designing robust interventions in CBs with unknown, fluctuating causal models.
method Proposes a robust CB algorithm with upper and lower bounds on regret.
result Achieves nearly optimal ildeO(T) ilde{\mathcal{O}}(\sqrt{T}) regret under certain conditions.

We achieve a finite regret bound of O(dlogd) for online inverse linear optimization with M-convex action sets.

problem Online inverse linear optimization with M-convex action sets.
method Combining structural characterization of optimal solutions on M-convex sets with geometric volume argument.
result Finite regret bound of O(dlogd) for online inverse linear optimization with M-convex action sets.

Study on online regression with noise, achieving near-optimal regret bounds.

problem Online generalized linear regression with stochastic noise.
method Sharp analysis of FTRL algorithm for stochastic label noise.
result Achieved near-optimal regret bounds for O(σ2dlogT)+o(logT)O(σ^2 d \log T) + o(\log T).

This paper addresses robust CBs for linear SEMs with model fluctuations.

problem Designing interventions in causal systems with linear SEMs that are robust to model fluctuations.
method Develops a robust CB algorithm and analyzes its regret under model deviation.
result The proposed algorithm achieves nearly optimal ildeO(T) ilde{\mathcal{O}}(\sqrt{T}) regret when CC is o(T)o(\sqrt{T}) and maintains sub-linear regret for a broader range of CC.

An algorithm tackles low-rank linear bandit problems with improved regret bounds.

problem Low-rank linear bandit problems where rewards are inner products with an unknown low-rank matrix.
method Combines online-to-confidence-set conversion and exponentially weighted average forecaster with a covering of low-rank matrices.
result Achieves O~((d1+d2)3/2rT)\widetilde{O}((d_1+d_2)^{3/2}\sqrt{rT}) regret, improving over standard bounds when rmin{d1,d2}r \ll \min\{d_1,d_2\}.

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 ↗

New algorithm learns LQR with O(T)O(\sqrt{T}) regret using Langevin dynamics and excitation.

problem Learning LQR with a O(T)O(\sqrt{T}) regret bound.
method Thompson sampling with Langevin dynamics and excitation mechanism.
result Achieved O(T)O(\sqrt{T}) regret bound for LQR learning.

New method for semiparametric bandits reduces regret to optimal levels.

problem Complex reward structures in semiparametric bandits.
method Experimental-design approach with sharp regret bound and PAC bound.
result Minimax regret of ildeO(dT) ilde{O}(\sqrt{dT}) and logarithmic regret under positive suboptimality gap.

New RL algorithm tackles nonstationary MDPs with linear approximations and varying rewards.

problem Nonstationary reinforcement learning with evolving reward and state transition functions.
method Developed a new algorithm LSVI-UCB-Restart with periodic restart, and parameter-free Ada-LSVI-UCB-Restart for unknown variation budgets.
result First minimax dynamic regret lower bound for nonstationary linear MDPs and linear MDPs lower bound.

Linear contextual bandit is an important class of sequential decision making problems with a wide range of applications to recommender systems, online advertising, healthcare, and many other machine learning related tasks. While there is a lot of prior research, tight regret bounds of linear contextual bandit with infi…

2019-05-04abs ↗pdf ↗

New algorithm reduces regret for linear bandits with unknown noise variance.

problem Finding optimal actions in linear bandits with varying noise variance.
method Adaptive algorithm with Freedman-type concentration inequality and multi-layer structure.
result Achieves ildeO(dk=1Kσk2+d) ilde{O}(d \sqrt{\sum_{k = 1}^K σ_k^2} + d) regret for linear bandits.

Improved privacy in RL with near-optimal regret bounds.

problem Privacy-preserving reinforcement learning in personalized decision-making systems.
method Differentially private algorithm based on LSVI-UCB++ with privacy-preserving techniques.
result Achieved a near-optimal regret bound of O(d * sqrt(H^3 * K) + H^(15/4) * d^(7/6) * K^(1/2) / ε).

The paper minimizes Borda regret in dueling bandits models.

problem Minimizing Borda regret in dueling bandits models.
method Proposes explore-then-commit and EXP3-type algorithms for stochastic and adversarial settings respectively.
result Achieves nearly matching regret upper bounds of O(d2/3T2/3)O(d^{2/3} T^{2/3}) for both settings.

LinMED is a new linear bandit algorithm with near-optimal regret bound.

problem Optimizing decision-making in linear bandit problems with sub-Gaussian distributions.
method LinMED is a randomized linear bandit algorithm with closed-form arm sampling probabilities.
result LinMED achieves a near-optimal regret bound of dnd\sqrt{n} up to logarithmic factors.