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

4080119159 · May 202619922001200920172026
48 results for projection oracle

Paper develops methods for non-quadratic loss low-rank matrix recovery.

problem Recovery of low-rank matrices with non-quadratic losses.
method Projected gradient method with a regularity projection oracle.
result Projected gradient method converges globally and linearly.

We propose in this paper a general framework for deriving loss functions for structured prediction. In our framework, the user chooses a convex set including the output space and provides an oracle for projecting onto that set. Given that oracle, our framework automatically generates a corresponding convex and smooth l…

2019-10-24abs ↗pdf ↗

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.

Improved method reduces projection calls for nonsmooth convex optimization.

problem Optimizing nonsmooth convex functions with convex constraints.
method MOPES and MOLES methods combining Moreau-Yosida smoothing and accelerated first-order schemes.
result Achieves εε-suboptimality with significantly fewer projection calls.

New algorithms optimize actions under time-varying constraints without projecting.

problem Optimizing actions under time-varying constraints without projecting.
method Projection-free algorithms using linear optimization oracle.
result Guaranteed ildeO(T3/4) ilde{O}(T^{3/4}) regret and O(T7/8)O(T^{7/8}) constraints violation.

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.

New algorithm solves complex optimization problems without needing projections.

problem Optimizing nested functions under convex constraints with noisy evaluations.
method Projection-free conditional gradient-type algorithm for smooth stochastic multi-level composition optimization.
result The algorithm achieves εε-stationary solutions with complexity bounds independent of εε and TT.

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 ↗

Study efficient algorithms for nonconvex optimization with state-dependent Markov data.

problem Stochastic optimization with Markovian data and state-dependent transition kernels.
method Projection-based and projection-free algorithms for constrained nonconvex problems.
result The number of oracle calls to achieve an εε-stationary point is O(1/ε2.5)\mathcal{O}(1/ε^{2.5}).

Study mini-batch SGD noise and its limits, proving complexity guarantees.

problem Analyzing the noise in mini-batch SGD and its impact on optimization.
method Examined the conditional covariance and diffusion limits of SGD under different sampling designs.
result Proved mean-square upper bounds and Fisher van Trees lower bounds for SGD, linking them to effective dimension and condition number.

In this work we introduce a conditional accelerated lazy stochastic gradient descent algorithm with optimal number of calls to a stochastic first-order oracle and convergence rate O(1ε2)O\left(\frac{1}{\varepsilon^2}\right) improving over the projection-free, Online Frank-Wolfe based stochastic gradient descent of Hazan an…

2017-03-16abs ↗pdf ↗

A new algorithm for solving constrained convex optimization problems efficiently.

problem Constrained convex optimization problems requiring high accuracy solutions.
method Second-Order Conditional Gradient Sliding (SOCGS) algorithm, using projection-free methods to solve quadratic subproblems inexactly.
result Converges quadratically in primal gap after a finite number of linearly convergent iterations.

Develops a new fairness learning approach for multi-task regression models.

problem Fairness in multi-task regression models with biased datasets.
method Uses rank-based non-parametric independence test (Mann Whitney U statistic) and reformulates as non-convex optimization problem.
result Outperforms state-of-the-art methods on fairness metrics.

Zeroth-order optimization methods lack inherent privacy guarantees.

problem Ensuring differential privacy in zeroth-order optimization methods.
method Analyzing ZO-GD with and without random initialization for convex and strongly convex objectives.
result ZO-GD is not differentially private for strongly convex objectives and can have superlinear privacy loss.

Local LMO optimizes constrained problems using local linear minimization.

problem Constrained optimization problems with complex feasible sets.
method Designs a new projection-free gradient method using local linear minimization.
result Transfers convergence rates of Projected Gradient Descent to the projection-free world.

Develops asymptotic theory for deep Cox models to enable valid inference.

problem Theoretical gaps in deep neural network estimators for Cox models.
method Asymptotic distribution theory linking in-sample optimization error to population risk.
result Pointwise and multivariate asymptotic normality for subsampled ensemble estimators.

A new method solves variational inequality problems with multiple constraints without needing optimal Lagrange multipliers.

problem Solving variational inequality problems with multiple functional constraints efficiently.
method Constrained Gradient Method (CGM) for Minty variational inequality problems.
result The Constrained Gradient Method achieves complexity similar to projection-based methods but with cheaper oracles.

New algorithms for multivariate RL improve decision-making in complex systems.

problem Complex multi-objective decision-making in reinforcement learning.
method Oracle-free and computationally-tractable algorithms for multivariate distributional RL.
result Convergence rates match scalar reward settings and provide insights into reward dimensionality.

New PG methods tackle nonconvex optimization with auto-conditioned stepsizes.

problem Optimizing nonconvex functions over convex sets.
method Auto-conditioned projected gradient (AC-PG) methods and stochastic variants.
result Achieved optimal iteration complexity for finding approximate stationary points.

New framework for decentralized optimization of upper-linearizable functions with improved regret and complexity.

problem Decentralized optimization of upper-linearizable functions with general constraints.
method Decentralized projection-free optimization with upper-linearizable function framework.
result Regret of O(T1θ/2)O(T^{1-θ/2}) with communication complexity of O(Tθ)O(T^θ) and linear optimization calls of O(T2θ)O(T^{2θ}).

Algorithm minimizes loss and constraint violations in online convex optimization with smooth penalties.

problem Minimizing loss and constraint violations in online convex optimization with smooth penalties.
method Projected gradient descent over a set around the current action.
result Both dynamic regret and constraint violation are bounded by the path-length.

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.

A discrete diffusion model learns denoising, scoring, and bridging in different coordinates.

problem Understanding what a discrete diffusion model learns in different coordinate systems.
method Rigorous derivation of continuous-time Markov chain ELBO, Oracle Distance theorem, and exact coordinates for optimizer.
result The negative ELBO is exactly equal to the data entropy plus the path KL from the oracle reverse process to the learned one.

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.

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.

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 desirable property of interpretable models is small size, so that they are easily understandable by humans. This leads to the following challenges: (a) small sizes typically imply diminished accuracy, and (b) bespoke levers provided by model families to restrict size, e.g., L1 regularization, might be insufficient to…

2019-06-17abs ↗pdf ↗

Max-min margin Markov networks improve consistency in structured prediction.

problem Statistical inconsistency in max-margin methods for structured prediction.
method Defining a max-min margin formulation to overcome statistical inconsistency.
result Proves consistency and provides an explicit algorithm with finite sample generalization bounds.

New oracle uses uncertainty for active classification with noisy feedback.

problem Improving query complexity in interactive binary classifier learning.
method Proposes a new pairwise comparison oracle that considers uncertainty and an adaptive labeling algorithm.
result Demonstrates improved performance and efficiency compared to existing methods.

Quantum oracles help identify counterfactuals better than classical ones.

problem Identifying unknown causal parameters in causal models.
method Using quantum oracles to query and identify all causal parameters and counterfactuals.
result Quantum oracles enable identification of all two-way joint counterfactuals and tighter bounds on higher-order counterfactuals.

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.

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.

FSPA bypasses eigenvalue estimation for quantum PCA, achieving optimal complexity and robustness.

problem Quantum PCA eigenvalue estimation is computationally expensive and prone to errors.
method Filtered Spectral Projection Algorithm (FSPA) that projects onto the dominant spectral subspace directly.
result FSPA achieves optimal complexity and robustness, outperforming classical methods.

New study shows Gaussian samplers struggle with heavy-tailed targets, while stable samplers excel.

problem The difficulty of sampling from heavy-tailed distributions using Gaussian versus stable oracles.
method Comparison of Gaussian and stable oracles for proximal samplers.
result Gaussian samplers have a fundamental barrier for high-accuracy guarantees in heavy-tailed sampling, while stable samplers excel.

Deep Jump Gaussian Processes model high-dimensional piecewise functions.

problem Modeling high-dimensional piecewise continuous functions with limited accuracy.
method Integrates region-specific locally linear projections with Jump Gaussian Processes (JGP) to capture local low-dimensional subspace structures.
result DJGP achieves superior predictive accuracy and more reliable uncertainty quantification compared to existing methods.