Picture for Anna Choromanska

Anna Choromanska

Adjacent Leader Decentralized Stochastic Gradient Descent

Add code
May 18, 2024
Viaarxiv icon

GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models

Add code
Mar 07, 2024
Figure 1 for GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models
Figure 2 for GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models
Figure 3 for GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models
Figure 4 for GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models
Viaarxiv icon

TAME: Task Agnostic Continual Learning using Multiple Experts

Add code
Oct 08, 2022
Figure 1 for TAME: Task Agnostic Continual Learning using Multiple Experts
Figure 2 for TAME: Task Agnostic Continual Learning using Multiple Experts
Figure 3 for TAME: Task Agnostic Continual Learning using Multiple Experts
Figure 4 for TAME: Task Agnostic Continual Learning using Multiple Experts
Viaarxiv icon

ERASE-Net: Efficient Segmentation Networks for Automotive Radar Signals

Add code
Sep 26, 2022
Figure 1 for ERASE-Net: Efficient Segmentation Networks for Automotive Radar Signals
Figure 2 for ERASE-Net: Efficient Segmentation Networks for Automotive Radar Signals
Figure 3 for ERASE-Net: Efficient Segmentation Networks for Automotive Radar Signals
Figure 4 for ERASE-Net: Efficient Segmentation Networks for Automotive Radar Signals
Viaarxiv icon

Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape

Add code
Feb 04, 2022
Figure 1 for Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape
Figure 2 for Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape
Figure 3 for Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape
Figure 4 for Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape
Viaarxiv icon

AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop

Add code
Dec 13, 2021
Figure 1 for AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop
Figure 2 for AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop
Figure 3 for AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop
Figure 4 for AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop
Viaarxiv icon

A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs

Add code
May 05, 2021
Figure 1 for A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs
Figure 2 for A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs
Figure 3 for A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs
Figure 4 for A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs
Viaarxiv icon

Backdoor Attacks on the DNN Interpretation System

Add code
Dec 03, 2020
Figure 1 for Backdoor Attacks on the DNN Interpretation System
Figure 2 for Backdoor Attacks on the DNN Interpretation System
Figure 3 for Backdoor Attacks on the DNN Interpretation System
Figure 4 for Backdoor Attacks on the DNN Interpretation System
Viaarxiv icon

Continual learning with direction-constrained optimization

Add code
Nov 25, 2020
Figure 1 for Continual learning with direction-constrained optimization
Figure 2 for Continual learning with direction-constrained optimization
Figure 3 for Continual learning with direction-constrained optimization
Figure 4 for Continual learning with direction-constrained optimization
Viaarxiv icon

SGB: Stochastic Gradient Bound Method for Optimizing Partition Functions

Add code
Nov 03, 2020
Figure 1 for SGB: Stochastic Gradient Bound Method for Optimizing Partition Functions
Viaarxiv icon