conftrace_

second-order optimization

93 papers

Explore in graph

Co-occurring keywords

newton method (64) natural gradient (75) stochastic optimization (1060) hessian approximation (41) kronecker factorization (18) fisher information matrix (46) second-order method (38) neural network optimization (1293) neural network training (309) gradient descent (1144)

Papers

Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training AAAI 2026
FedPM: Federated Learning Using Second-order Optimization with Preconditioned Mixing of Local Parameters AAAI 2026
Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin ICCV 2025
Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs SEMEVAL 2025
Fast Second-Order Online Kernel Learning Through Incremental Matrix Sketching and Decomposition IJCAI 2025
On Adaptive Stochastic Optimization for Streaming Data: A Newton's Method with O(dN) Operations JMLR 2025
Communication Efficient Distributed Newton Method over Unreliable Networks AAAI 2024
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning EMNLP 2024
Sketched Newton Value Iteration for Large-Scale Markov Decision Processes AAAI 2024
Second-order forward-mode optimization of recurrent neural networks for neuroscience NIPS 2024
Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate AISTATS 2024
VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models EMNLP 2024
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks NIPS 2024
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization NIPS 2024
Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression NIPS 2024
A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks NIPS 2024
Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms NIPS 2024
The Challenges of the Nonlinear Regime for Physics-Informed Neural Networks NIPS 2024
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information NIPS 2024
Black Box Variational Inference with a Deterministic Objective: Faster, More Accurate, and Even More Black Box JMLR 2024
Second-Order Optimization with Lazy Hessians ICML 2023
Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions NIPS 2023
Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning ICML 2023
Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures NIPS 2023
Krylov–Bellman boosting: Super-linear policy evaluation in general state spaces AISTATS 2023