Alert button
Picture for Virginia Smith

Virginia Smith

Alert button

Lessons from Chasing Few-Shot Learning Benchmarks: Rethinking the Evaluation of Meta-Learning Methods

Feb 23, 2021
Amrith Setlur, Oscar Li, Virginia Smith

Figure 1 for Lessons from Chasing Few-Shot Learning Benchmarks: Rethinking the Evaluation of Meta-Learning Methods
Figure 2 for Lessons from Chasing Few-Shot Learning Benchmarks: Rethinking the Evaluation of Meta-Learning Methods
Figure 3 for Lessons from Chasing Few-Shot Learning Benchmarks: Rethinking the Evaluation of Meta-Learning Methods
Figure 4 for Lessons from Chasing Few-Shot Learning Benchmarks: Rethinking the Evaluation of Meta-Learning Methods
Viaarxiv icon

Label Leakage and Protection in Two-party Split Learning

Feb 17, 2021
Oscar Li, Jiankai Sun, Xin Yang, Weihao Gao, Hongyi Zhang, Junyuan Xie, Virginia Smith, Chong Wang

Figure 1 for Label Leakage and Protection in Two-party Split Learning
Figure 2 for Label Leakage and Protection in Two-party Split Learning
Figure 3 for Label Leakage and Protection in Two-party Split Learning
Figure 4 for Label Leakage and Protection in Two-party Split Learning
Viaarxiv icon

Federated Multi-Task Learning for Competing Constraints

Dec 08, 2020
Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith

Figure 1 for Federated Multi-Task Learning for Competing Constraints
Figure 2 for Federated Multi-Task Learning for Competing Constraints
Figure 3 for Federated Multi-Task Learning for Competing Constraints
Figure 4 for Federated Multi-Task Learning for Competing Constraints
Viaarxiv icon

Is Support Set Diversity Necessary for Meta-Learning?

Nov 28, 2020
Amrith Setlur, Oscar Li, Virginia Smith

Figure 1 for Is Support Set Diversity Necessary for Meta-Learning?
Figure 2 for Is Support Set Diversity Necessary for Meta-Learning?
Figure 3 for Is Support Set Diversity Necessary for Meta-Learning?
Viaarxiv icon

Tilted Empirical Risk Minimization

Jul 02, 2020
Tian Li, Ahmad Beirami, Maziar Sanjabi, Virginia Smith

Figure 1 for Tilted Empirical Risk Minimization
Figure 2 for Tilted Empirical Risk Minimization
Figure 3 for Tilted Empirical Risk Minimization
Figure 4 for Tilted Empirical Risk Minimization
Viaarxiv icon

FedDANE: A Federated Newton-Type Method

Jan 07, 2020
Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith

Figure 1 for FedDANE: A Federated Newton-Type Method
Figure 2 for FedDANE: A Federated Newton-Type Method
Figure 3 for FedDANE: A Federated Newton-Type Method
Figure 4 for FedDANE: A Federated Newton-Type Method
Viaarxiv icon

Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches

Dec 06, 2019
Tian Li, Zaoxing Liu, Vyas Sekar, Virginia Smith

Figure 1 for Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
Figure 2 for Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
Figure 3 for Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
Figure 4 for Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
Viaarxiv icon

Enhancing the Privacy of Federated Learning with Sketching

Nov 05, 2019
Zaoxing Liu, Tian Li, Virginia Smith, Vyas Sekar

Figure 1 for Enhancing the Privacy of Federated Learning with Sketching
Figure 2 for Enhancing the Privacy of Federated Learning with Sketching
Figure 3 for Enhancing the Privacy of Federated Learning with Sketching
Figure 4 for Enhancing the Privacy of Federated Learning with Sketching
Viaarxiv icon

Progressive Compressed Records: Taking a Byte out of Deep Learning Data

Nov 01, 2019
Michael Kuchnik, George Amvrosiadis, Virginia Smith

Figure 1 for Progressive Compressed Records: Taking a Byte out of Deep Learning Data
Figure 2 for Progressive Compressed Records: Taking a Byte out of Deep Learning Data
Figure 3 for Progressive Compressed Records: Taking a Byte out of Deep Learning Data
Figure 4 for Progressive Compressed Records: Taking a Byte out of Deep Learning Data
Viaarxiv icon