📈 Optimization - jyunzhang · Scour

Flatland: The Adventures of Gradient Descent with Large Step Sizes

🧠Deep Learning Academic

Quantifying Uncertainty In Wide Two-Layer Neural Networks: On The Law Of The Limiting Fluctuation Process

🧠Deep Learning Academic

Stain-Aware Wavelet Regularization for Instant Adversarial Purification in Histopathology

🤖Machine Learning Academic

An Ensembled Latent Factor Model via Differential Evolution and Gradient Descent Optimization

🤖LLMs Academic

ARAPDiffusion: ARAP Regularization for Diffusion-Based Deformable Shape Space Learning

🤖AI Academic

Preserving Plasticity in Continual Learning via Dynamical Isometry

🧠Deep Learning Academic

Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent

🧠Deep Learning Academic

Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws

🤖LLMs Academic

Gradient descent at the Edge of Stability: free energy model and kinetic description of the two-layer network

🧠Deep Learning Academic

Closed-Form Spectral Regularization for Multi-Task Model Merging

📐Linear Algebra Academic

Predictive Coding with Bayesian Priors via Proximal Gradients

🤖Machine Learning Academic

Structure-Aware Prediction of PROTAC-Mediated Protein Degradability via Graph Neural Networks

🧠Deep Learning Academic

Noise-Adaptive High-Probability Regret Bounds for Online Convex Optimization

🎮Reinforcement Learning Academic

Pretraining Recurrent Networks without Recurrence

🤖Machine Learning Academic

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

🧠Deep Learning Academic

Rethinking the Divergence Regularization in LLM RL

🎮Reinforcement Learning Academic

When Do Fewer Coordinates Suffice in DP-SGD?

🤖LLMs Academic

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

🤖AI Academic

Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD

🔐Cryptography Academic

Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning

🧠Deep Learning Academic

Log in to enable infinite scrolling