5.1k citations · 9.6k across the 102 of their papers we have counts for
13 papers · 1 filter
Differentially Private Meta-Learning
Jeffrey Li, Mikhail Khodak, Sebastian Caldas +1
Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However,…
Federated Learning: Challenges, Methods, and Future Directions
Tian Li, Anit Kumar Sahu, Ameet Talwalkar +1
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in he…
Learning Fair Representations for Kernel Models
Zilong Tan, Samuel Yeom, Matt Fredrikson +1
Fair representations are a powerful tool for establishing criteria like statistical parity, proxy non-discrimination, and equality of opportunity in learned models. Existing techni…
Adaptive Gradient-Based Meta-Learning Methods
Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar
We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive…
Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)
Gregory Plumb, Maruan Al-Shedivat, Eric Xing +1
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post…
MLSys: The New Frontier of Machine Learning Systems
Alexander Ratner, Dan Alistarh, Gustavo Alonso +66
Machine learning (ML) techniques are enjoying rapidly increasing adoption. However, designing and implementing the systems that support ML models in real-world deployments remains…
On the support recovery of marginal regression
S. Jalil Kazemitabar, Arash A. Amini, Ameet Talwalkar
Leading methods for support recovery in high-dimensional regression, such as Lasso, have been well-studied and their limitations in the context of correlated design have been chara…
Exploiting Reuse in Pipeline-Aware Hyperparameter Tuning
Liam Li, Evan Sparks, Kevin Jamieson +1
Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden. Motivated by the observation that work can be reused across pipelines if the intermedi…
One-Shot Federated Learning
Neel Guha, Ameet Talwalkar, Virginia Smith
We present one-shot federated learning, where a central server learns a global model over a network of federated devices in a single round of communication. Our approach - drawing…
Provable Guarantees for Gradient-Based Meta-Learning
Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar
We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and…
Random Search and Reproducibility for Neural Architecture Search
Liam Li, Ameet Talwalkar
Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In this wor…
Regularizing Black-box Models for Improved Interpretability
Gregory Plumb, Maruan Al-Shedivat, Angel Alexander Cabrera +3
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post…
Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
Sebastian Caldas, Jakub Konečny, H. Brendan McMahan +1
Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation. To address this issue,…