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

count % of corpus

5 results for “parameter-agnostic”

Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimizationmath.OC

NeAda solves nonconvex minimax optimization by balancing primal and dual variables adaptively.

problem Nonconvex minimax optimization challenges with parameter-agnostic adaptive algorithms.

method Nested Adaptive (NeAda) framework with inner and outer loops for primal and dual variables.

result Achieves near-optimal convergence rates for nonconvex-strongly-concave problems.

nonconvex minimax adaptive optimization parameter-agnostic convergence rates NeAda

2022-06-01abs ↗pdf ↗

Parameter-Agnostic Optimization under Relaxed Smoothnessmath.OC

NSGD-M optimizes machine learning models without hyperparameter tuning, even under relaxed smoothness.

problem Training machine learning models with optimal complexity under relaxed smoothness assumptions.

method Normalized Stochastic Gradient Descent with Momentum (NSGD-M) without stepsize tuning.

result NSGD-M achieves nearly optimal complexity without prior knowledge of problem parameters.

machine learning optimization parameter-agnostic smoothness convergence

2023-11-06abs ↗pdf ↗

TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimizationmath.OC

TiAda adapts adaptive gradient methods for nonconvex minimax optimization.

problem Nonconvex minimax optimization challenges in achieving convergence.

method TiAda is a time-scale adaptive GDA algorithm for nonconvex minimax optimization.

result TiAda achieves near-optimal complexities in deterministic and stochastic settings.

nonconvex minimax optimization adaptive gradient methods time-scale separation convergence analysis

2022-10-31abs ↗pdf ↗

Categorical Distributions of Maximum Entropy under Marginal Constraintshep-th

A framework estimates categorical distributions under constraints, ensuring generality and uniqueness.

problem Estimating categorical distributions summarizing sample data under marginal constraints.

method Theoretical framework + Iterative Proportional Fitting (IPF) to estimate the distribution.

result A unique categorical distribution of Maximum Entropy under marginal constraints exists and is estimated.

Maximum Entropy Marginal Constraints Iterative Proportional Fitting Categorical Distributions Machine Learning

2022-04-07abs ↗pdf ↗

Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Methodcs.LG

Ringmaster LMO accelerates training in distributed systems by asynchronously updating neural networks.

problem Asynchronous training in distributed systems where workers compute gradients at different speeds.

method Introduces an asynchronous LMO-based momentum method for unconstrained stochastic nonconvex optimization.

result Establishes convergence guarantees and time complexity bounds for asynchronous LMO-based updates.

asynchronous training distributed systems LMO method momentum nonconvex optimization

2026-05-18abs ↗pdf ↗