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

201403604805 · Jun 202019922001200920172026
48 results for optimization oracle

New oracles improve stochastic optimization with noisy or biased measurements.

problem Optimizing functions with noisy or biased measurements.
method Introduced biased gradient oracles for stochastic optimization, analyzed RSG and SGD algorithms with these oracles.
result Derived non-asymptotic bounds for convergence rates of algorithms with biased gradient oracles.

MAMBA learns policies competitive with multiple conflicting oracles.

problem Learning policies from multiple conflicting oracles in reinforcement learning.
method MAMBA uses a gradient estimator in the style of GAE to optimize policies, leveraging demonstrations from multiple weak oracles.
result MAMBA outperforms the state-of-the-art in learning policies competitive with multiple conflicting oracles.

New analysis shows Thompson Sampling can work with greedy approximations in combinatorial bandits.

problem Thompson Sampling's theoretical limits with greedy approximations in combinatorial semi-bandits.
method Study with greedy oracle, providing lower and upper bounds on regret.
result First theoretical results showing TS can work with greedy approximations, breaking misconceptions.

Improved Frank-Wolfe algorithm for constrained convex optimization with nearest extreme point oracle.

problem Constrained smooth convex minimization with limited linear optimization oracle access.
method Frank-Wolfe algorithm with nearest extreme point oracle.
result Improved complexity bounds for specific feasible sets, including linear convergence for 0ext10 ext{--}1 polytopes.

We consider online learning in an adversarial, non-convex setting under the assumption that the learner has an access to an offline optimization oracle. In the general setting of prediction with expert advice, Hazan et al. (2016) established that in the optimization-oracle model, online learning requires exponentially …

2018-10-17abs ↗pdf ↗

Study on gradient complexity of private optimization with private oracles.

problem Analyzing the efficiency of differentially private optimization algorithms.
method Lower bounds on the number of first-order oracle queries for private optimization.
result Lower bounds on the number of queries for private optimization algorithms, showing a dimension-dependent runtime penalty.

Three new oracle-efficient algorithms for private synthetic data release.

problem Constructing private synthetic data that preserves statistical query answers.
method Oracle-efficient algorithms using optimization oracles for differential privacy.
result Better accuracy in large workload and high privacy regime compared to state-of-the-art.

We give nearly matching upper and lower bounds on the oracle complexity of finding εε-stationary points (F(x)ε\| \nabla F(x) \| \leqε) in stochastic convex optimization. We jointly analyze the oracle complexity in both the local stochastic oracle model and the global oracle (or, statistical learning) model. This allows u…

2019-02-13abs ↗pdf ↗

Paper addresses online alignment of large language models under uncertain preference feedback.

problem Online alignment of large language models with misspecified preference feedback.
method Formulates an oracle-robust objective as a worst-case optimization problem for log-linear policies, and develops projected stochastic composite updates.
result Shows that the robust objective admits an exact closed-form decomposition and achieves O~(ε2)\widetilde{O}(\varepsilon^{-2}) oracle complexity.

We revisit the question of reducing online learning to approximate optimization of the offline problem. In this setting, we give two algorithms with near-optimal performance in the full information setting: they guarantee optimal regret and require only poly-logarithmically many calls to the approximation oracle per it…

2018-04-20abs ↗pdf ↗

Oracle-efficient algorithm for offline RL with partial data coverage.

problem Offline reinforcement learning with partial data coverage and constraints.
method PDOCRL, a primal-dual algorithm with decomposed linear-programming formulation.
result Near-optimal, near-feasible policy with \(\widetilde{\mathcal O}(ε^{-2})\) sample guarantee.

Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.

problem Scalability issue in combinatorial semi-bandit problems due to high combinatorial optimization costs.
method Oracle-efficient frameworks that minimize oracle queries while maintaining tight regret guarantees.
result Achieved ildeO(T) ilde{O}(\sqrt{T}) regret with O(loglogT)O(\log\log T) oracle queries for worst-case linear rewards.

New algorithms ensure reproducibility and optimal convergence in convex optimization.

problem Trade-off between reproducibility and convergence rate in convex optimization.
method Regularization-based algorithms for smooth convex minimization and minimax optimization.
result Achieves optimal reproducibility and near-optimal gradient complexity for various oracle settings.

We provide tight upper and lower bounds on the complexity of minimizing the average of mm convex functions using gradient and prox oracles of the component functions. We show a significant gap between the complexity of deterministic vs randomized optimization. For smooth functions, we show that accelerated gradient de…

2016-05-25abs ↗pdf ↗

New algorithms reduce reinforcement learning regret in factored MDPs.

problem Optimizing reinforcement learning in non-episodic factored MDPs.
method Proposed two near-optimal and oracle-efficient algorithms for FMDPs.
result Oracle-efficient algorithms achieve near-optimal regret bounds of O(DSAT)O(DS\sqrt{AT}).

Algorithm solves online binary classification and infinite games using ERM oracle.

problem Online learning and solving infinite games with computationally inefficient oracles.
method Proposes an algorithm relying solely on ERM oracle calls for online binary classification and nonparametric games.
result Achieves finite and sublinearly growing regret in various settings.

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder bu…

2017-04-19abs ↗pdf ↗

A new Bayesian method optimizes time-dependent expensive functions with lookahead.

problem Maximizing a time-dependent, expensive oracle with limited evaluations.
method Recursive, two-step lookahead expected payoff (r2LEY) acquisition function.
result r2LEY outperforms myopic methods in synthetic and real-world datasets.

Folded concave penalization methods have been shown to enjoy the strong oracle property for high-dimensional sparse estimation. However, a folded concave penalization problem usually has multiple local solutions and the oracle property is established only for one of the unknown local solutions. A challenging fundamenta…

2012-10-22abs ↗pdf ↗

Study on costs of manipulating AMM-based price oracles.

problem Cost of manipulation in AMM-based on-chain price oracles.
method Analyzes the robustness of AMM-based oracles to strategic manipulation, considering different aggregation methods and market conditions.
result Manipulation costs depend on the total quote depth and can be minimized by optimal liquidity weights.

GPE algorithm optimizes nonparametric contextual bandits with efficient regret bounds.

problem Optimizing nonparametric contextual bandits with efficient regret bounds.
method Inspired by Policy Elimination, GPE uses oracle-efficient techniques for nonparametric classes with infinite VC-dimension.
result GPE is regret-optimal for policy classes with integrable entropy, and for larger entropy, it provides an ε\varepsilon-greedy algorithm with matching regret bounds.

This paper tackles bandit optimization with a new pairwise comparison oracle for unknown strongly concave functions.

problem Maximizing an unknown strongly concave function over T periods with a biased pairwise comparison oracle.
method Introduced a discretization technique and local polynomial approximation to relate the problem to linear bandits. Developed a tournament successive elimination technique to localize the discretized cell and run LinUCB algorithm on cells.
result Established optimal regret bounds and improved state-of-the-art results in operations management problems.

Lower bounds found for nonconvex-strongly-concave min-max optimization problems.

problem Finding stationary points in nonconvex-strongly-concave min-max optimization.
method Provided lower bounds for first-order oracle complexity.
result Lower bounds of Ω(√κε⁻²) for deterministic oracles and Ω(√κε⁻² + κ¹/₃ε⁻⁴) for stochastic oracles.

New algorithm for clustering with faulty oracle achieves optimal queries and efficiency.

problem Clustering with a faulty oracle, especially for multiple clusters.
method Built on stochastic block model, provides nearly-optimal query complexity.
result Time-efficient algorithm with nearly-optimal query complexity for all constant k and any δ.

Oracle inequality for sparse neural nets adapts to unknown structure.

problem Sparse deep neural nets in nonparametric regression.
method Gibbs posterior distribution with Metropolis-adjusted Langevin algorithms and mixture of uniform priors.
result Oracle inequality showing adaptation to unknown regularity and structure, achieving minimax-optimal rate of convergence.

Develops accelerated methods for optimization using low-dimensional projected-gradient information.

problem Optimization with low-dimensional projected-gradient information and Nesterov acceleration.
method Randomized-subspace Nesterov accelerated gradient methods for smooth convex and strongly convex optimization.
result Established accelerated oracle-complexity guarantees and unified basis for comparing sketch families.

Gradient descent is efficient for solving feasibility problems with minimal memory and queries.

problem Finding a point in a given set using a memory-constrained algorithm with a separation oracle.
method Oracle complexity lower bounds for gradient descent and other algorithms.
result Gradient descent is Pareto-optimal in the oracle complexity/memory tradeoff for feasibility problems.

Improved algorithm finds second-order stationary points in non-convex optimization.

problem Minimizing non-convex objectives while preserving training data privacy.
method SpiderBoost framework with two gradient oracles: precise and less precise.
result Improved rates for finding second-order stationary points.

New algorithms solve stochastic variational inequalities without bounded variance assumption.

problem Solving stochastic variational inequalities without bounded variance assumption.
method Developed algorithms for two classes of problems: monotone and structured nonmonotone VIs.
result Oracle complexity of O(ε^-4) for solving VIs with unbounded domains and possibly unbounded variance.