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.

168,742 papers · 148 categories

Trend · papers per month

248496744992 · Jun 202019922001200920172026
48 results for optimal point

Paper analyzes algorithms for nonstationary saddle-point optimization problems.

problem Nonstationary saddle-point optimization problems in game theory, reinforcement learning, and machine learning.
method Proposes extragradient and Frank-Wolfe algorithms for online and bandit settings.
result Establishes sub-linear regret bounds for the proposed algorithms.

Adam optimizer fails to stay close to optimal point under certain conditions.

problem Adam optimizer's tendency to deviate from the optimal point in training neural networks.
method Analyzed Adam's behavior in convex regions and proposed a new algorithm to correct this.
result Adam optimizer cannot stay close to the optimal point when effective learning rate exceeds a certain bound.

Gradient-based optimization methods are the most popular choice for finding local optima for classical minimization and saddle point problems. Here, we highlight a systemic issue of gradient dynamics that arise for saddle point problems, namely the presence of undesired stable stationary points that are no local optima…

2018-05-15abs ↗pdf ↗

We optimize saddle-point problems for large-scale Markov decision processes.

problem Optimizing policies in large-scale Markov decision processes.
method Characterized conditions for convergence and designed an optimization algorithm.
result Our algorithm converges faster and is state-space independent.

Proposes a novel approach for cluster-aware matching using Laplacian Optimal Transport.

problem Matching point clouds with intrinsic cluster structure requires robust region-to-region alignment over precise point-to-point correspondence.
method Laplacian Optimal Transport (LapOT) with regularization for cluster-aware matching and Refined Simultaneous Clustering (RSC) for consistent partitions.
result Laplacian Optimal Transport produces more consistent and meaningful alignments between point clouds.

New methods help escape strict saddle points in nonsmooth optimization.

problem Escaping strict saddle points in nonsmooth optimization.
method An inexact stochastically perturbed gradient method applied to the Moreau envelope.
result A variety of algorithms for nonsmooth optimization can efficiently escape strict saddle points of the Moreau envelope.

This paper improves Bayesian optimization by using pseudo-points to enhance model accuracy.

problem Expensive black-box optimization problems, especially in parameter tuning and experimental design.
method Generates pseudo-points to improve Gaussian process models in Bayesian optimization.
result Cumulative regret can be generally upper bounded using the proposed framework.

FeDualEx tackles saddle point optimization in federated learning with composite objectives.

problem Saddle point optimization with constraints and non-smooth regularization in federated learning.
method Federated Dual Extrapolation (FeDualEx) algorithm for saddle point optimization and composite objectives.
result FeDualEx effectively solves saddle point optimization problems with composite objectives in federated learning.

Poor (even random) starting points for learning/training/optimization are common in machine learning. In many settings, the method of Robbins and Monro (online stochastic gradient descent) is known to be optimal for good starting points, but may not be optimal for poor starting points -- indeed, for poor starting point…

2016-02-09abs ↗pdf ↗

A new one-point feedback scheme improves ZO algorithms for black-box optimization.

problem Optimizing black-box functions without gradient information.
method Proposes a one-point feedback scheme to estimate gradients using residuals.
result Matches query complexity of two-point schemes for deterministic Lipschitz functions.

New ODE models show saddle-point optimization methods converge differently, with last-iterate convergence for OGDA.

problem Analyzing convergence properties of saddle-point optimization methods.
method High-Resolution Differential Equations (HRDEs) to design differential equation models for saddle-point optimization methods.
result HRDEs reveal last-iterate convergence for Optimistic Gradient Descent Ascent (OGDA) in bilinear games.

New meta-optimizer learns from both point-based and population-based algorithms.

problem Current meta-optimizers are limited in space and unaware of uncertainty.
method Proposes a new meta-optimizer that learns in the space of both point-based and population-based algorithms, targeting a meta-loss function of cumulative regret and entropy.
result Empirical results show superior performance over existing competitors.

The recent developments of basis pursuit and compressed sensing seek to extract information from as few samples as possible. In such applications, since the number of samples is restricted, one should deploy the sampling points wisely. We are motivated to study the optimal distribution of finite sampling points. Formul…

2012-07-25abs ↗pdf ↗

New method finds stationary points in bilevel optimization problems.

problem Solving nonconvex-strongly-convex bilevel optimization problems.
method Restarted Accelerated HyperGradient Descent (RAHGD) method.
result Achieves best-known theoretical guarantees for finding stationary points in bilevel optimization.

This paper tackles the computational complexity of finding approximate stationary points in non-convex optimization.

problem Finding approximate stationary points in non-convex optimization problems.
method PLS-completeness, zero-order algorithms, and gradient queries.
result The query complexity of finding approximate stationary points is Θ(1/ε) for d=2.

GenFlow optimizes faster, avoiding saddle points in fixed time.

problem Designing efficient optimization algorithms for convex and non-convex functions.
method Introduces GenFlow and momentum variants with fixed-time convergence guarantees.
result GenFlow and momentum variants converge to optimal solutions in fixed time for PL functions and evade saddle points uniformly.

Optimizes bond portfolios to avoid worst-case losses.

problem Finding the worst-case value of a bond portfolio over a range of yield curves and spreads.
method Solves a convex-concave saddle point optimization problem to find the worst-case value and construct a robust portfolio.
result Constructs a bond portfolio that includes the worst-case value, ensuring robustness against market uncertainties.

Linear speedup achieved in non-convex optimization for decentralized systems.

problem Achieving optimal performance in decentralized non-convex optimization.
method Examined the dependence of convergence guarantees on spectral properties of combination policies.
result Linear speedup in saddle-point escape time for symmetric combination policies.

Novel optimization method detects change points in Gaussian data.

problem Detecting change points in univariate Gaussian data sequences.
method Continuous optimization for best subset selection (COMBSS) applied to a reformulated statistical inverse problem.
result Adaptation and evaluation of COMBSS for offline normal mean multiple change-point detection.

New method simplifies optimization landscapes by transforming saddle points.

problem Saddle points hinder non-convex optimization in machine learning.
method Variable elimination algorithms, like VarPro, are compared to reveal geometric insights.
result Variable elimination reshapes critical point structure, creating local maxima from saddle points.

Paper optimizes change-point detection using learned distributions from training sequences.

problem Optimal change-point detection with unknown pre- and post-change distributions.
method Designs a change-point estimator using training sequences and test sequences.
result Optimal confidence width characterized as a function of undetected error.

IPO optimizes reinforcement learning with constraints for better performance.

problem Maximizing long-term reward while satisfying cumulative constraints in decision problems.
method Interior-point Policy Optimization (IPO) using logarithmic barrier functions.
result IPO outperforms state-of-the-art baselines in reward maximization and constraint satisfaction.

We analyze critical points of the Sliced Wasserstein Distance for optimization stability.

problem Understanding the behavior of optimization algorithms for models trained with the Sliced Wasserstein Distance.
method Explicit perturbations and critical point analysis of the SW objective.
result Stable critical points of SW cannot concentrate on segments, providing optimization stability.

Bayesian optimization with Gaussian processes speeds up searches for stationary points.

problem Accelerating searches for stationary points on potential energy surfaces.
method Unified Bayesian optimization view using Gaussian process regression with derivative observations, inverse-distance kernels, and active learning.
result Surrogates can reduce the number of expensive electronic structure evaluations by an order of magnitude.

Paper proposes estimating gradients for zeroth-order nonconvex optimization.

problem Oracle access of gradients is limited in many applications.
method Develops a gradient descent method using estimated gradients.
result Algorithm finds second-order stationary points efficiently.

The paper tackles finding stationary points in stochastic convex optimization problems.

problem Finding stationary points for stochastic convex optimization problems.
method The approach relies on dimension theory to decompose the graph of the subdifferential of a convex function, showing how stochastic sampling preserves 'pieces' of these graphs, and allowing effective application of proximal-point-like methods.
result The paper provides convergence guarantees for finding stationary points in stochastic convex optimization problems.

In many applications of black-box optimization, one can evaluate multiple points simultaneously, e.g. when evaluating the performances of several different neural network architectures in a parallel computing environment. In this paper, we develop a novel batch Bayesian optimization algorithm --- the parallel knowledge…

2016-06-14abs ↗pdf ↗

New algorithms find near-stationary points in convex optimization.

problem Finding near-stationary points in convex optimization.
method Memory-saving variant of OGM-G, accelerated SVRG, adaptively regularized accelerated SVRG.
result Schemes achieve fast rates for minimizing gradient norm and function value.

We consider online detection strategies for identifying a change point in a stream of quantum particles allegedly prepared in identical states. We show that the identification of the change point can be done without error via sequential local measurements while attaining the optimal performance bound set by quantum mec…

2018-02-01abs ↗pdf ↗

Lower bounds on queries needed for finding stationary points in non-convex optimization.

problem Finding εε-stationary points in non-convex stochastic optimization.
method Proving lower bounds on the number of queries required by stochastic first-order methods.
result Lower bounds on the number of queries required to find εε-stationary points are tight and optimal.

DPP-BBO diversifies batched Bayesian optimization using DPPs.

problem Efficiently proposing diverse and informative batches in batched Bayesian optimization.
method Introducing DPP-Batch Bayesian Optimization (DPP-BBO) with DPP-Thompson Sampling (DPP-TS).
result Novel Bayesian simple regret bounds for DPP-TS show improved performance over classical methods.

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.