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

74148222296 · Jun 202019922001200920172026
48 results for first-order guarantees

New sampling method guarantees approximate first-order stationary points for non-convex functions.

problem Sampling from non-log-concave densities with non-convex potential functions.
method Averaged Langevin Monte Carlo with complexity analysis.
result Langevin Monte Carlo outputs a sample with ε-relative Fisher information after O(L²d²/ε²) iterations.

Develops first-order methods for average-reward MDPs with strong guarantees.

problem Lack of strong theoretical guarantees for first-order methods in AMDPs.
method Average-reward stochastic policy mirror descent (SPMD) and variance-reduced temporal difference (VRTD) methods.
result Establishes sample complexity results for solving AMDPs.

New algorithm reduces online decision-making regret with efficient LP re-solving and parallel first-order method.

problem Worse regret guarantees and high computational cost of LP-based OLP algorithms.
method Combines LP-based and first-order OLP methods, re-solving LP subproblems periodically and using parallel first-order method.
result Achieves O(log(T/f)+f)\mathscr{O}(\log (T/f) + \sqrt{f}) regret, balancing computational efficiency and superior regret guarantee.

Second-order guarantees for federated learning algorithms.

problem Non-convex optimization in federated learning with saddle-points as bottlenecks.
method Drawing on recent results on second-order optimality in centralized and decentralized settings, establish second-order guarantees for federated learning algorithms.
result Established second-order guarantees for federated learning algorithms.

New method predicts state evolution for non-first-order algorithms on nonconvex problems.

problem Analyzing nonconvex optimization problems with random data.
method Developed a state evolution for a broader class of algorithms including first-order and saddle point updates.
result Established rigorous state evolution predictions and finite-sample guarantees for non-first-order methods.

Develops a first-order interior-point method for solving constrained variational inequalities.

problem Solving constrained variational inequalities with nontrivial constraints.
method ADMM-based interior-point method for constrained VIs (ACVI).
result First-order interior-point method with global convergence guarantees for general cVI problems.

First-order method solves stochastic bilevel optimization with linear constraints.

problem Stochastic bilevel optimization with linear constraints and noise.
method Developed a novel framework using gradient-based techniques and smoothed penalty functions.
result Achieved finite-time convergence guarantees for (δ,ε)(δ, ε)-Goldstein stationary points.

Variance reduction techniques like SVRG provide simple and fast algorithms for optimizing a convex finite-sum objective. For nonconvex objectives, these techniques can also find a first-order stationary point (with small gradient). However, in nonconvex optimization it is often crucial to find a second-order stationary…

2019-05-01abs ↗pdf ↗

New algorithm guarantees optimal convergence rate for stochastic optimization.

problem Optimal convergence rate for stochastic optimization algorithms.
method Regularized versions of Minimization by Incremental Surrogate Optimization (MISO) with arbitrary recurrent data sampling.
result Expected optimality gap converges at O(n1/2)O(n^{-1/2}) under general recurrent sampling schemes.

A new first-order sampler improves diffusion probabilistic model sampling quality.

problem The belief that first-order methods are inherently slower for diffusion probabilistic model sampling.
method A novel training-free, first-order sampler that approximates the forward-value evaluation via a one-step lookahead predictor.
result The proposed sampler provably approximates the ideal forward-value trajectory while retaining first-order convergence and can improve sample quality under the same NFE budget.

OptEx accelerates first-order optimization with parallelized iterations.

problem Inefficiencies in first-order optimization algorithms for complex tasks.
method Approximately parallelized iterations using kernelized gradient estimation.
result OptEx achieves substantial efficiency improvements with an effective acceleration rate of Ω(N)Ω(\sqrt{N}).

Paper develops fast method for computing optimal transport.

problem Efficient computation of optimal transport distance between distributions.
method Entropy-regularized extragradient method for first-order optimization.
result Achieves state-of-the-art runtime guarantees and good numerical performance.

Paper investigates conditions for independence of weak gradients on metric spaces.

problem Dependence of weak gradients on pp in arbitrary metric measure spaces.
method Investigates the Bounded Interpolation Property to ensure independence of weak gradients.
result Bounded Interpolation Property guarantees independence of weak gradients.

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}).

The paper explores how topology affects the solvability of first-order differential equations.

problem The solvability of first-order differential equations and the role of topology.
method Analysis of de Rham cohomology to determine global integrability and uniqueness of solutions.
result Triviality of the first de Rham cohomology group is a fundamental requirement for global integrability and uniqueness of solutions.

GANs excel at learning high dimensional distributions, but they can update generator parameters in directions that do not correspond to the steepest descent direction of the objective. Prominent examples of problematic update directions include those used in both Goodfellow's original GAN and the WGAN-GP. To formally d…

2018-02-13abs ↗pdf ↗

New methods reduce constraint violations to certainty in stochastic optimization.

problem Finding a point with certain constraint satisfaction and near-stationarity.
method Single-loop variance-reduced stochastic first-order methods with truncated momentum schemes.
result Achieves strong convergence guarantees for εε-stochastic stationary points with certain constraint satisfaction.

Many problems in machine learning and game theory can be formulated as saddle-point problems, for which various first-order methods have been developed and proven efficient in practice. Under the general convex-concave assumption, most first-order methods only guarantee an ergodic convergence rate, that is, the uniform…

2019-03-26abs ↗pdf ↗

New algorithm achieves data-dependent regret bounds in MDPs with unknown transitions.

problem Achieving best-of-both-worlds guarantees with data-dependent regret bounds in MDPs with unknown transitions.
method Optimistic follow-the-regularized-leader algorithm with new optimistic Q-function estimators and transition bonus.
result First-order, second-order, and path-length bounds with polylog(T) regret in the stochastic regime.

Compensation methods correct overestimation of adversarial robustness in neural networks.

problem Overestimation of adversarial robustness using first-order attack methods.
method Proposed compensation methods address inaccurate gradient computation and reduce backpropagations.
result Empirical evaluation of adversarial robustness is improved with these methods.

New method accelerates convergence for entropy-regularized reinforcement learning problems.

problem Slow convergence of standard first-order methods for entropy-regularized Markov decision processes.
method Introduce a quadratically convexified primal-dual formulation and a new interpolating metric to accelerate convergence.
result Global convergence and exponential convergence rate for the new method.

Paper discusses optimal CP for second-order predictions.

problem How to incorporate second-order predictions into conformal prediction.
method Introduces Bernoulli prediction sets (BPS) for second-order predictions and applies conformal risk control for compromised validity.
result BPS provides the smallest prediction sets with conditional coverage.

Flow-based models generate data with improved theoretical guarantees.

problem Theoretical analysis of flow-based generative models.
method Proximal gradient descent in Wasserstein space for JKO flow model.
result KL guarantee of data generation by JKO flow model is O(ε2)O(\varepsilon^2).

Improved KL bounds and Wasserstein guarantees for diffusion flow matching under minimal conditions.

problem Theoretical convergence properties of Brownian motion based diffusion flow matching.
method Refined analysis under Kullback-Leibler and 2-Wasserstein distances.
result State-of-the-art scaling in KL convergence bounds under minimal conditions.

This paper analyzes bias-variance trade-off for clipped SFOMs, improving complexity guarantees for heavy-tailed noise.

problem Improving complexity guarantees for stochastic optimization methods with heavy-tailed noise.
method Novel analysis of bias-variance trade-off in gradient clipping for clipped SFOMs.
result Improved complexity guarantees for clipped SFOMs across various tail indices, including infinite mean noise.

This paper analyzes convergence of RMSProp and Adam in non-convex optimization with tight complexity bounds.

problem Analyzing convergence of RMSProp and Adam in non-convex optimization with relaxed assumptions.
method Developed new convergence analyses for RMSProp and Adam, considering adaptive learning rates and affine noise variance.
result RMSProp and Adam converge to ε-stationary points with iteration complexities of O(ε^(-4)) under proper hyperparameters.

Finite-sum optimization problems are ubiquitous in machine learning, and are commonly solved using first-order methods which rely on gradient computations. Recently, there has been growing interest in \emph{second-order} methods, which rely on both gradients and Hessians. In principle, second-order methods can require …

2016-11-15abs ↗pdf ↗

We propose a family of optimization methods that achieve linear convergence using first-order gradient information and constant step sizes on a class of convex functions much larger than the smooth and strongly convex ones. This larger class includes functions whose second derivatives may be singular or unbounded at th…

2018-09-13abs ↗pdf ↗

Improved Metropolized HMC runtime for logconcave distributions.

problem Improving the runtime of Metropolized HMC for logconcave sampling.
method Gradient norm concentration and new mixing time analysis techniques.
result Metropolized HMC mixes in O~(κd)\tilde{O}(κd) iterations, improving runtime by a factor of (κ/d)1/2(κ/d)^{1/2}.

New analysis improves understanding of bilevel optimization stability and generalization.

problem Understanding how well bilevel optimization algorithms generalize.
method Algorithmic stability arguments and generalization bounds for three bilevel minimax solvers.
result Precise trade-off between algorithmic stability, generalization gaps, and practical settings.

Paper tackles bilevel optimization problems using penalty methods.

problem Unconstrained and constrained bilevel optimization problems with nonsmooth lower levels.
method Introduces first-order penalty methods and O(ε4logε1)O(\varepsilon^{-4}\log\varepsilon^{-1}) and O(ε7logε1)O(\varepsilon^{-7}\log\varepsilon^{-1}) operation complexities.
result Establishes operation complexities for finding ε\varepsilon-KKT solutions.

New methods for convex optimization with locally Lipschitz gradient, achieving faster convergence.

problem Optimization problems with locally Lipschitz continuous gradient.
method Accelerated proximal gradient (APG) methods and proximal augmented Lagrangian method.
result Achieved faster convergence rates for convex optimization problems with locally Lipschitz gradient.

We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated with its decisions. After making each decision, the learner observes the losses associated with its a…

2015-02-23abs ↗pdf ↗