📐 Optimization Theory - yfff · Scour

Near-Optimal Decentralized Stochastic Convex Optimization over Networks

📐Semidefinite Programming Academic

OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality

📐Semidefinite Programming Academic

The Spectral Dynamics and Noise Geometry of Muon

🧠Machine Learning Academic

When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks

🧠Machine Learning Academic

Improved Convergence Analysis of Topology Dependence in Decentralized SGD

📉Loss Landscapes Academic

A Theory on Flow Matching with Neural Networks

🧠Machine Learning Academic

Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD

🧠Machine Learning Academic

Duality for Optimal Multi-Item, Multi-Bidder Auction Design: Revenue Certificates through Deep Learning

🧠Machine Learning Academic

A prism hierarchy of learning regimes in large linear autoencoders

🧠Machine Learning Academic

Variational Proximal Policy Optimization

🎮Reinforcement Learning Academic

Learning Dynamics Reveal a Hierarchy of Weight-Induced Layerwise Gram Metrics

🧠Machine Learning Academic

When Do Fewer Coordinates Suffice in DP-SGD?

🧠Machine Learning Academic

Fourier fractal dimension to predict the generalization of deep neural networks

🧠Machine Learning Academic

Constrained Paraphrase Consistency for LLM Hallucination Detection

🧠Machine Learning Academic

PL-KKT-hPINN: Enforcing Nonlinear Equality Constraints on Neural Networks via Piecewise-Linear Projection

🧠LLM Academic

On the conditional equivalence of phase retrieval algorithms

🧠Machine Learning Academic

A Mean-Field Analysis of Multi-Head Self-Attention under Cross-Entropy Training

🤖Transformers Academic

Reinforcement Learning for Flow-Matching Policies with Density Transport

🤖AI Academic

Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning

🎮Reinforcement Learning Academic

Beyond Linear and Overcomplete Regimes: A Mean-Field Analysis of Bottleneck Autoencoders

🧠Machine Learning Academic

Log in to enable infinite scrolling