Optimal Trade

Optimal trade-off analysis focuses on identifying and managing the inherent conflicts between multiple, often competing objectives within a system. Current research emphasizes developing algorithms and models, such as Pareto-optimal algorithms and Bayesian optimization techniques, to find the best balance between these objectives across diverse applications, including machine learning model robustness and accuracy, multi-objective optimization, and resource allocation in robotics and microgrids. These advancements have significant implications for improving the efficiency and performance of various systems while simultaneously addressing constraints like computational cost, privacy concerns, and ethical considerations.

Papers

December 27, 2022

Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs
Souvik Kundu, Sairam Sundaresan, Sharath Nittur Sridhar, Shunlin Lu, Han Tang, Peter A. Beerel
Deep Neural Network Native Robustness Adversarial Training Adversarial Image Optimal Trade Sparse Mask

July 23, 2022

A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors
Nikhil Ghosh, Mikhail Belkin
Model Size Overparametrization Bound Optimal Trade Training Loss Linear Predictor Test Loss

July 16, 2022

Parallel Best Arm Identification in Heterogeneous Environments
Nikolai Karpov, Qin Zhang
Multiple Agent Collaborative Learning Best Arm Identification Optimal Trade Heterogeneous Environment Heterogeneous Learning

June 9, 2022

Principal Trade-off Analysis
Alexander Strang, David SeWell, Alexander Kim, Kevin Alcedo, David Rosenbluth
General Analysis Two Player Zero Sum Optimal Trade CEO Personality

June 2, 2022

Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates
Jacob Portes, Davis Blalock, Cory Stephenson, Jonathan Frankle
Optimal Trade Training Time Cyclic Learning Training Network

May 3, 2022

Revisiting Communication-Efficient Federated Learning with Balanced Global and Local Updates
Zhigang Yan, Dong Li, Zhichao Zhang, Jiguang He
Loss Function Global Context Local Model Local Context Optimal Trade Global Aggregation

March 28, 2022

A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness
Souvik Kundu, Sairam Sundaresan, Massoud Pedram, Peter A. Beerel
Adversarial Attack Native Robustness Adversarial Training Convolution Operation Optimal Trade Return Conditioned Supervised Learning Standard Adversarial Training

February 2, 2022

Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference
Jasper Tan, Blake Mason, Hamid Javadi, Richard G. Baraniuk
Membership Inference Attack Privacy Policy Many Parameter Membership Inference Overparametrization Bound Optimal Trade Ridge Regularized

December 22, 2021

Evolution and trade-off dynamics of functional load
Erich Round, Rikker Dockum, Robin J. Ryder
Specie Evolution Optimal Trade Dynamic Loading Phonological Feature Diachronic Semantic

December 12, 2021

Cold Item Integration in Deep Hybrid Recommenders via Tunable Stochastic Gates
Oren Barkan, Roy Hirsch, Ori Katz, Avi Caciularu, Jonathan Weill, Noam Koenigstein
Deep Learning Collaborative Filtering Optimal Trade Hybrid Recommendation Stochastic Gate

Optimal Trade

Papers

Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs

A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors

Parallel Best Arm Identification in Heterogeneous Environments

Principal Trade-off Analysis

Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates

Revisiting Communication-Efficient Federated Learning with Balanced Global and Local Updates

A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness

Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference

Evolution and trade-off dynamics of functional load

Cold Item Integration in Deep Hybrid Recommenders via Tunable Stochastic Gates