FINDER: Stochastic Mirroring of Noisy Quasi-Newton Search and Deep Network Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Suman, Uttam, Mamajiwala, Mariya, Saxena, Mukul, Tyagi, Ankit, Roy, Debasish
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Physics Informed Deep Learning for Strain Gradient Continuum Plasticity
by: Tyagi, Ankit, et al.
Published: (2024)

Stochastic Approximation and Brownian Repulsion based Evolutionary Search
by: Dutta, Rajdeep, et al.
Published: (2024)

FINDER: Feature Inference on Noisy Datasets using Eigenspace Residuals
by: Murphy, Trajan, et al.
Published: (2025)

Exact Gauss-Newton Optimization for Training Deep Neural Networks
by: Korbit, Mikalai, et al.
Published: (2024)

OASIS: Online Activation Subspace Learning for Memory-Efficient Training
by: Choudhary, Sakshi, et al.
Published: (2026)

A Stochastic Quasi-Newton Method for Non-convex Optimization with Non-uniform Smoothness
by: Sun, Zhenyu, et al.
Published: (2024)

Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
by: Lu, Haoye, et al.
Published: (2025)

LightTopoGAT: Enhancing Graph Attention Networks with Topological Features for Efficient Graph Classification
by: Sharma, Ankit, et al.
Published: (2025)

Noisy Low Rank Column-wise Sensing
by: Singh, Ankit Pratap, et al.
Published: (2024)

Dynamic Sparse Training of Diagonally Sparse Networks
by: Tyagi, Abhishek, et al.
Published: (2025)

Continual Learning With Quasi-Newton Methods
by: Eeckt, Steven Vander, et al.
Published: (2025)

A Universal Banach--Bregman Framework for Stochastic Iterations: Unifying Stochastic Mirror Descent, Learning and LLM Training
by: Zhang, Johnny R., et al.
Published: (2025)

A Lightweight Deep Learning Model for Automatic Modulation Classification using Dual Path Deep Residual Shrinkage Network
by: Suman, Prakash, et al.
Published: (2025)

GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training
by: Tyagi, Sahil, et al.
Published: (2023)

Sharpened Lazy Incremental Quasi-Newton Method
by: Lahoti, Aakash, et al.
Published: (2023)

Distributed Quasi-Newton Method for Fair and Fast Federated Learning
by: Hamidi, Shayan Mohajer, et al.
Published: (2025)

KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction
by: Saxena, Utkarsh, et al.
Published: (2025)

OmniLearn: A Framework for Distributed Deep Learning over Heterogeneous Clusters
by: Tyagi, Sahil, et al.
Published: (2025)

Stochastic Newton Proximal Extragradient Method
by: Jiang, Ruichen, et al.
Published: (2024)

Improving Stochastic Cubic Newton with Momentum
by: Chayti, El Mahdi, et al.
Published: (2024)

Generalized Random Direction Newton Algorithms for Stochastic Optimization
by: Pachal, Soumen, et al.
Published: (2026)

Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training
by: Tyagi, Sahil, et al.
Published: (2026)

Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates
by: Liu, Zhuanghua, et al.
Published: (2024)

Self-Scaled Broyden Family of Quasi-Newton Methods in JAX
by: Bioli, Ivan, et al.
Published: (2026)

Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees
by: Agafonov, Artem, et al.
Published: (2025)

Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization
by: Ranganath, Aditya, et al.
Published: (2025)

Implicit Bias and Convergence of Matrix Stochastic Mirror Descent
by: Akhtiamov, Danil, et al.
Published: (2026)

Deep Learning Classification With Noisy Labels
by: Sanchez, Guillaume, et al.
Published: (2020)

Tracking Equivalent Mechanistic Interpretations Across Neural Networks
by: Sun, Alan, et al.
Published: (2026)

Quasi-Newton Compatible Actor-Critic for Deterministic Policies
by: Kordabad, Arash Bahari, et al.
Published: (2025)

Q-Newton: Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent
by: Li, Pingzhi, et al.
Published: (2024)

Painless Federated Learning: An Interplay of Line-Search and Extrapolation
by: Geetika, et al.
Published: (2024)

A Proximal Modified Quasi-Newton Method for Nonsmooth Regularized Optimization
by: Diouane, Youssef, et al.
Published: (2024)

Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
by: Chen, Sijia, et al.
Published: (2023)

On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars
by: Tao, Chun, et al.
Published: (2021)

Harmonic Loss Trains Interpretable AI Models
by: Baek, David D., et al.
Published: (2025)

UAV Trajectory Optimization via Improved Noisy Deep Q-Network
by: Hengyu, Zhang, et al.
Published: (2026)

Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks
by: Kliachkin, Andrii, et al.
Published: (2025)

A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks
by: Agostinelli, Forest, et al.
Published: (2021)

A Complete Characterization of Learnability for Stochastic Noisy Bandits
by: Hanneke, Steve, et al.
Published: (2024)