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

100199299398 · Jun 202019922001200920172026
48 results for Suboptimality Bounds

New study shows exponential lower bound for RL even with constant suboptimality gap.

problem Can RL be sample-efficient with a constant suboptimality gap?
method Analyzes reinforcement learning in the online setting with a linearly realizable optimal Q-function.
result An exponential sample complexity lower bound still holds even with a constant suboptimality gap.

Paper explores limits of imitation learning in MDPs, setting new suboptimality bounds.

problem Understanding the statistical limits of imitation learning in MDPs.
method Analyzes minimax statistical limits in two settings: pre-interaction and interaction.
result Establishes suboptimality bounds for imitation learning in MDPs, showing improvements with knowledge of transition.

New algorithm reduces suboptimality in imitation learning to nearly optimal levels.

problem Statistical limits of imitation learning in MDPs with known transitions.
method Mimic-MD algorithm and reduction to value estimation problem.
result Upper bound of O(SH3/2/N)O(|\mathcal{S}|H^{3/2}/N) for suboptimality, with efficient computation.

Research aims to improve confidence intervals for RKHS elements in online learning.

problem Improper confidence intervals lead to suboptimal regret bounds in kernel-based bandit and reinforcement learning.
method Formalizes the open problem of online confidence intervals in RKHS and reviews existing results.
result Identifies the online nature of observation points as the main challenge for tight confidence intervals.

Least Squares Estimators are suboptimal for 5D convex functions.

problem Suboptimality of Least Squares Estimators in estimating multidimensional convex functions.
method Analysis of natural subclasses of convex functions in random and fixed design settings.
result Risk of LSE is n2/dn^{-2/d} while minimax risk is n4/(d+4)n^{-4/(d+4)} for d5d \geq 5.

Boltzmann exploration is a classic strategy for sequential decision-making under uncertainty, and is one of the most standard tools in Reinforcement Learning (RL). Despite its widespread use, there is virtually no theoretical understanding about the limitations or the actual benefits of this exploration scheme. Does it…

2017-05-29abs ↗pdf ↗

We develop a robust RL algorithm for off-dynamics environments with improved suboptimality bounds and computational efficiency.

problem Learning policies robust to uncertainties in transition dynamics between training and deployment environments.
method Distributionally robust Markov decision processes (DRMDPs) with a novel algorithm We-DRIVE-U.
result Improved suboptimality bound of O~(dHmin{1/ρ,H}/K)\widetilde{\mathcal{O}}\big({d H \cdot \min \{1/ρ, H\}/\sqrt{K} }\big), near-optimal up to O(H)\mathcal{O}(\sqrt{H}).

Novel IRL method identifies suboptimal medical decisions in ICU data.

problem Identifying suboptimal medical decisions in clinical settings.
method Incorporates Inverse Reinforcement Learning with a pruning step to identify and remove suboptimal actions.
result Pruning step effectively identifies clinical priorities and values from suboptimal data.

In this paper, we propose and study opportunistic bandits - a new variant of bandits where the regret of pulling a suboptimal arm varies under different environmental conditions, such as network load or produce price. When the load/price is low, so is the cost/regret of pulling a suboptimal arm (e.g., trying a suboptim…

2017-09-12abs ↗pdf ↗

BILBO optimizes bilevel problems without repeated lower-level optimizations.

problem Challenges in bilevel optimization, especially in noisy, constrained, and derivative-free settings.
method BILevel Bayesian Optimization (BILBO) that optimizes both levels simultaneously, using confidence-bounds and function query selection.
result Theoretical and empirical evidence of BILBO's effectiveness on various problems.

Improved reinforcement learning for episodes with varying action sets.

problem Reinforcement learning with context-dependent action sets.
method Extends MVP algorithm to handle adversarial and stochastic contexts.
result Established minimax regret bounds of O(SAH3KlogL)O(\sqrt{SAH^3K\log L}) for adversarial contexts.

Proves a quantitative index theorem for positive scalar curvature metrics.

problem Studying conjectures and open questions on positive scalar curvature.
method Quantitative relative index theorem and λλ-Lipschitz rigidity theorem.
result Positive answers to Gromov's open questions on scalar curvature.

Optimality of TS with noninformative priors proven for Pareto model.

problem Optimality of Thompson Sampling with noninformative priors for Pareto bandits.
method Proved optimality of TS with certain probability matching priors, showed suboptimality with others, and found effectiveness of truncation procedures.
result TS with certain probability matching priors achieves optimal regret bound for Pareto model.

New suboptimal algorithm for best subset selection in high-dimensional data.

problem Nonconvex and computationally challenging best subset selection in linear regression.
method Introducing a new suboptimal algorithm and comparing it with other popular methods.
result The new procedure is a competitive suboptimal algorithm for high-dimensional data.

Fine-grained gap-dependent regret bounds for reinforcement learning.

problem Achieving optimal regret bounds for reinforcement learning with suboptimality gaps.
method Developed novel analytical frameworks and refined algorithms for UCB-based and non-UCB-based reinforcement learning.
result Established the first fine-grained gap-dependent regret bounds for both UCB-based and non-UCB-based algorithms.

There has been substantial research on sub-linear time approximate algorithms for Maximum Inner Product Search (MIPS). To achieve fast query time, state-of-the-art techniques require significant preprocessing, which can be a burden when the number of subsequent queries is not sufficiently large to amortize the cost. Fu…

2018-12-15abs ↗pdf ↗

Several probabilistic models from high-dimensional statistics and machine learning reveal an intriguing --and yet poorly understood-- dichotomy. Either simple local algorithms succeed in estimating the object of interest, or even sophisticated semi-definite programming (SDP) relaxations fail. In order to explore this p…

2016-10-17abs ↗pdf ↗

New method solves complex optimization problems faster.

problem Minimizing a convex smooth objective over the optimal solution set of another convex smooth problem.
method Uses a cutting plane approach to approximate the lower-level problem and an accelerated gradient method to update the upper-level objective.
result Shows that the method requires at most O(max{1/εf,1/εg})\mathcal{O}(\max\{1/\sqrt{ε_{f}}, 1/ε_g\}) iterations to achieve εfε_f-suboptimality and εgε_g-infeasibility.

Unified framework for risk-aware policy learning in contextual bandits.

problem Optimizing decision rules in high-stakes domains with adverse outcomes.
method Distributional framework for Lipschitz-continuous risk functionals, with novel empirical concentration inequalities.
result Data-dependent suboptimality bounds with an ildeO(1/n) ilde{\mathcal{O}}(1/\sqrt{n}) rate, matching risk-neutral offline policy optimization.

Paper tackles RLHF with DCPPO method, proving near-optimal suboptimality.

problem Challenges in offline RLHF with limited human feedback and bounded rationality.
method DCPPO method involving three stages: MLE, reward function recovery, and pessimistic value iteration.
result DCPPO's suboptimality almost matches classical pessimistic offline RL in terms of distribution shift and dimension.

The maximum a posteriori (MAP) configuration of binary variable models with submodular graph-structured energy functions can be found efficiently and exactly by graph cuts. Max-product belief propagation (MP) has been shown to be suboptimal on this class of energy functions by a canonical counterexample where MP conver…

2011-05-05abs ↗pdf ↗

Develops a Best-of-Both-Worlds algorithm for linear contextual bandits with Tsallis entropy.

problem Linear contextual bandits with i.i.d. contexts.
method Follow-The-Regularized-Leader (FTRL) with Tsallis entropy.
result Achieves $O\left(\log(T)^{\frac{1+β}{2+β}}T^{\frac{1}{2+β}} ight)$ regret under margin condition.

Privacy-preserving reinforcement learning from human feedback using decoupled reward modeling.

problem Training large language models with sensitive user information while preserving privacy.
method Proposes a privacy-preserving framework that imposes differential privacy on reward learning only.
result Privacy contributes an additional additive term to the suboptimality gap, and the upper bound is rate-optimal up to logarithmic factors.

Paper studies offline RL with linear approx, focusing on inherent Bellman error.

problem Offline RL with linear approx, focusing on inherent Bellman error.
method Algorithm that succeeds under single-policy coverage condition, leveraging inherent Bellman error.
result Algorithm yields first known guarantee under single-policy coverage, even for linear Bellman completeness.

New algorithm estimates edge density of random graphs robustly, achieving optimal breakdown point.

problem Estimating edge density of Erdős-Rényi graphs under adversarial edge manipulation.
method Sum-of-Squares (SoS) hierarchy, constructing constant-degree certificates for concentration.
result First polynomial-time algorithm with optimal breakdown point and matching error guarantees.

We propose a novel combination of optimization tools with learning theory bounds in order to analyze the sample complexity of optimal kernel sum classifiers. This contrasts the typical learning theoretic results which hold for all (potentially suboptimal) classifiers. Our work also justifies assumptions made in prior w…

2019-01-25abs ↗pdf ↗

Optimal algorithm for high-dimensional stochastic linear bandits with sparse parameters.

problem High-dimensional stochastic linear bandits with sparse parameters.
method Three-stage arm selection algorithm using thresholded Lasso for estimation.
result Achieves exact minimax optimality in cumulative regret.

This paper extends the work in [Suzuki, 1996] and presents an efficient depth-first branch-and-bound algorithm for learning Bayesian network structures, based on the minimum description length (MDL) principle, for a given (consistent) variable ordering. The algorithm exhaustively searches through all network structures…

2013-01-16abs ↗pdf ↗

Study quantile multi-armed bandits for identifying the best arm with a specified quantile level.

problem Identifying the arm with the highest quantile in multi-armed bandits with private rewards.
method Proposed a (non-private) and differentially private successive elimination algorithms for best-arm identification.
result The proposed algorithms are essentially optimal for quantile bandit problems, with finite sample complexity even for distributions with infinite support-size.