Summary of Curvature-informed Sgd Via General Purpose Lie-group Preconditioners, by Omead Pooladzandi and Xi-lin Li
Curvature-Informed SGD via General Purpose Lie-Group Preconditionersby Omead Pooladzandi, Xi-Lin LiFirst submitted to arxiv on:…
Summary of Stochastic Modified Flows For Riemannian Stochastic Gradient Descent, by Benjamin Gess et al.
Stochastic Modified Flows for Riemannian Stochastic Gradient Descentby Benjamin Gess, Sebastian Kassing, Nimit RanaFirst submitted…
Summary of Momentum Does Not Reduce Stochastic Noise in Stochastic Gradient Descent, by Naoki Sato and Hideaki Iiduka
Momentum Does Not Reduce Stochastic Noise in Stochastic Gradient Descentby Naoki Sato, Hideaki IidukaFirst submitted…
Summary of Metaoptimize: a Framework For Optimizing Step Sizes and Other Meta-parameters, by Arsalan Sharifnassab et al.
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parametersby Arsalan Sharifnassab, Saber Salehkaleybar, Richard…
Summary of Emergence Of Heavy Tails in Homogenized Stochastic Gradient Descent, by Zhe Jiao et al.
Emergence of heavy tails in homogenized stochastic gradient descentby Zhe Jiao, Martin Keller-ResselFirst submitted to…
Summary of Truncated Non-uniform Quantization For Distributed Sgd, by Guangfeng Yan et al.
Truncated Non-Uniform Quantization for Distributed SGDby Guangfeng Yan, Tan Li, Yuanzhang Xiao, Congduan Li, Linqi…
Summary of Continuous-time Riemannian Sgd and Svrg Flows on Wasserstein Probabilistic Space, by Mingyang Yi et al.
Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Spaceby Mingyang Yi, Bohan WangFirst submitted…
Summary of A Precise Characterization Of Sgd Stability Using Loss Surface Geometry, by Gregory Dexter et al.
A Precise Characterization of SGD Stability Using Loss Surface Geometryby Gregory Dexter, Borja Ocejo, Sathiya…
Summary of Wasserstein Differential Privacy, by Chengyi Yang et al.
Wasserstein Differential Privacyby Chengyi Yang, Jiayin Qi, Aimin ZhouFirst submitted to arxiv on: 23 Jan…
Summary of The Dimension Strikes Back with Gradients: Generalization Of Gradient Methods in Stochastic Convex Optimization, by Matan Schliserman and Uri Sherman and Tomer Koren
The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimizationby Matan…