🎯 Optimization Theory - gautam6599123 · Scour

Parametric Nonconvex Optimization via Convex Surrogates 📊Optimization

arxiv.org·2d

Rational Matrix Iterations for Polar Decomposition 📐Linear Algebra

jiha-kim.github.io·4d·Hacker News

Low-Rank Key Value Attention: Reducing KV Cache Memory and Maintaining Head Diversity 🤖Transformers

fin.ai·23h·Hacker News

Grow and mow: interpretable models with boosting, symbolic regression and e-graphs ∂Automatic Differentiation

mchav.github.io·1d·Hacker News

Why Alignment Risk Might Peak Before ASI - a Substrate Controller Framework 🎮Reinforcement Learning

lesswrong.com·1d

An international mega-analysis of psychedelic drug effects on brain circuit function 📊Data Science

nature.com·2d·Hacker News

Duality and DeepMartingale for High-Dimensional Optimal Switching: Computable Upper Bounds and Approximation-Expressivity Guarantees 📊Optimization

arxiv.org·12h

Direct Preference Optimization for LLM Alignment 🗣️Large Language Models

hackernoon.com·2d

\texttt{DR-DAQP}: An Hybrid Operator Splitting and Active-Set Solver for Affine Variational Inequalities 📐Linear Algebra

arxiv.org·3d

The Training Example Lie Bracket ∂Automatic Differentiation

lesswrong.com·2d

Universal, sample-optimal algorithms for recovery of anisotropic functions from i.i.d. samples 📊Optimization

arxiv.org·12h

Local discontinuous Galerkin FEM for convex minimization 📊Optimization

arxiv.org·12h

Inversion-Free Natural Gradient Descent on Riemannian Manifolds ∂Automatic Differentiation

arxiv.org·4d

Conservation Law Breaking at the Edge of Stability: A Spectral Theory of Non-Convex Neural Network Optimization 📊Optimization

arxiv.org·12h

Variance-Reduced Gradient Estimator for Nonconvex Zeroth-Order Distributed Optimization 🔶TensorFlow

arxiv.org·12h

Verifying Well-Posedness of Linear PDEs using Convex Optimization ⛰️Convex Analysis

arxiv.org·3d

Density-Driven Optimal Control: Convergence Guarantees for Stochastic LTI Multi-Agent Systems 🌀Hamiltonian Mechanics

arxiv.org·12h

Toward a Uniform Algorithm and Uniform Reduction for Constraint Problems ⛰️Convex Analysis

arxiv.org·1d

A convergence rate for the entropic JKO scheme 📡Information Theory

arxiv.org·12h

Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates 📊Optimization

arxiv.org·1d

Loading more...