Ameet Talwalkar

research

∙ 04/13/2023

Learning Personalized Decision Support Policies

Individual human decision-makers may benefit from different forms of sup...

0 Umang Bhatt, et al. ∙

research

∙ 02/16/2023

Assisting Human Decisions in Document Matching

Many practical applications, ranging from paper-reviewer assignment in p...

0 Joon Sik Kim, et al. ∙

research

∙ 02/11/2023

Cross-Modal Fine-Tuning: Align then Refine

Fine-tuning large-scale pretrained models has led to tremendous progress...

0 Junhong Shen, et al. ∙

research

∙ 02/09/2023

Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning

Machine learning models with high accuracy on test data can still produc...

0 Ángel Alexander Cabrera, et al. ∙

research

∙ 12/17/2022

On Noisy Evaluation in Federated Hyperparameter Tuning

Hyperparameter tuning is critical to the success of federated learning a...

0 Kevin Kuo, et al. ∙

research

∙ 08/25/2022

SONAR: Joint Architecture and System Optimization Search

There is a growing need to deploy machine learning for different tasks o...

0 Elias Jääsaari, et al. ∙

research

∙ 07/20/2022

Provably tuning the ElasticNet across instances

An important unresolved challenge in the theory of regularization is to ...

0 Maria-Florina Balcan, et al. ∙

research

∙ 07/08/2022

Evaluating Systemic Error Detection Methods using Synthetic Images

We introduce SpotCheck, a framework for generating synthetic datasets to...

0 Gregory Plumb, et al. ∙

research

∙ 06/24/2022

On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods

Machine Learning (ML) models now inform a wide range of human decisions,...

13 Kasun Amarasinghe, et al. ∙

research

∙ 06/05/2022

Use-Case-Grounded Simulations for Explanation Evaluation

A growing body of research runs human subject evaluations to study wheth...

0 Valerie Chen, et al. ∙

research

∙ 05/27/2022

AANG: Automating Auxiliary Learning

When faced with data-starved or highly complex end-tasks, it is commonpl...

0 Lucio M. Dery, et al. ∙

research

∙ 05/13/2022

Perspectives on Incorporating Expert Feedback into Model Updates

Machine learning (ML) practitioners are increasingly tasked with develop...

0 Valerie Chen, et al. ∙

research

∙ 04/15/2022

Efficient Architecture Search for Diverse Tasks

While neural architecture search (NAS) has enabled automated machine lea...

0 Junhong Shen, et al. ∙

research

∙ 02/18/2022

Learning Predictions for Algorithms with Predictions

A burgeoning paradigm in algorithm design is the field of algorithms wit...

0 Mikhail Khodak, et al. ∙

research

∙ 12/12/2021

Bayesian Persuasion for Algorithmic Recourse

When subjected to automated decision-making, decision subjects may strat...

0 Keegan Harris, et al. ∙

research

∙ 10/12/2021

NAS-Bench-360: Benchmarking Diverse Tasks for Neural Architecture Search

Most existing neural architecture search (NAS) benchmarks and algorithms...

0 Renbo Tu, et al. ∙

research

∙ 09/15/2021

Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative

Pre-training, where models are trained on an auxiliary objective with ab...

0 Lucio M. Dery, et al. ∙

research

∙ 08/19/2021

Learning-to-learn non-convex piecewise-Lipschitz functions

We analyze the meta-learning of the initialization and step-size of lear...

0 Maria-Florina Balcan, et al. ∙

research

∙ 06/08/2021

Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing

Tuning hyperparameters is a crucial but arduous part of the machine lear...

0 Mikhail Khodak, et al. ∙

research

∙ 06/03/2021

Finding and Fixing Spurious Patterns with Explanations

Machine learning models often use spurious patterns such as "relying on ...

0 Gregory Plumb, et al. ∙

research

∙ 05/13/2021

Sanity Simulations for Saliency Methods

Saliency methods are a popular class of feature attribution tools that a...

0 Joon Sik Kim, et al. ∙

research

∙ 03/29/2021

Rethinking Neural Operations for Diverse Tasks

An important goal of neural architecture search (NAS) is to automate-awa...

7 Nicholas Roberts, et al. ∙

research

∙ 03/10/2021

Towards Connecting Use Cases and Methods in Interpretable Machine Learning

Despite increasing interest in the field of Interpretable Machine Learni...

0 Valerie Chen, et al. ∙

research

∙ 02/26/2021

Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

We empirically demonstrate that full-batch gradient descent on neural ne...

0 Jeremy M Cohen, et al. ∙

research

∙ 01/30/2021

On Data Efficiency of Meta-learning

Meta-learning has enabled learning statistical models that can be quickl...

8 Maruan Al-Shedivat, et al. ∙

research

∙ 11/02/2020

A Learning Theoretic Perspective on Local Explainability

In this paper, we explore connections between interpretable machine lear...

0 Jeffrey Li, et al. ∙

research

∙ 04/16/2020

Geometry-Aware Gradient Algorithms for Neural Architecture Search

Many recent state-of-the-art methods for neural architecture search (NAS...

23 Liam Li, et al. ∙

research

∙ 04/07/2020

Model-Agnostic Characterization of Fairness Trade-offs

There exist several inherent trade-offs in designing a fair model, such ...

0 Joon Sik Kim, et al. ∙

research

∙ 03/03/2020

Explaining Groups of Points in Low-Dimensional Representations

A common workflow in data exploration is to learn a low-dimensional repr...

20 Gregory Plumb, et al. ∙

research

∙ 01/07/2020

FedDANE: A Federated Newton-Type Method

Federated learning aims to jointly learn statistical models over massive...

0 Tian Li, et al. ∙

research

∙ 09/12/2019

Differentially Private Meta-Learning

Parameter-transfer is a well-known and versatile approach for meta-learn...

5 Jeffrey Li, et al. ∙

research

∙ 08/21/2019

Federated Learning: Challenges, Methods, and Future Directions

Federated learning involves training statistical models over remote devi...

9 Tian Li, et al. ∙

research

∙ 06/27/2019

Learning Fair Representations for Kernel Models

Fair representations are a powerful tool for establishing criteria like ...

2 Zilong Tan, et al. ∙

research

∙ 06/06/2019

Adaptive Gradient-Based Meta-Learning Methods

We build a theoretical framework for understanding practical meta-learni...

0 Mikhail Khodak, et al. ∙

research

∙ 05/31/2019

Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)

Most of the work on interpretable machine learning has focused on design...

5 Gregory Plumb, et al. ∙

research

∙ 03/29/2019

SysML: The New Frontier of Machine Learning Systems

Machine learning (ML) techniques are enjoying rapidly increasing adoptio...

0 Alexander Ratner, et al. ∙

research

∙ 03/22/2019

On the support recovery of marginal regression

Leading methods for support recovery in high-dimensional regression, suc...

0 S. Jalil Kazemitabar, et al. ∙

research

∙ 03/12/2019

Exploiting Reuse in Pipeline-Aware Hyperparameter Tuning

Hyperparameter tuning of multi-stage pipelines introduces a significant ...

18 Liam Li, et al. ∙

research

∙ 02/27/2019

Provable Guarantees for Gradient-Based Meta-Learning

We study the problem of meta-learning through the lens of online convex ...

14 Mikhail Khodak, et al. ∙

research

∙ 02/20/2019

Random Search and Reproducibility for Neural Architecture Search

Neural architecture search (NAS) is a promising research direction that ...

14 Liam Li, et al. ∙

research

∙ 02/18/2019

Regularizing Black-box Models for Improved Interpretability

Most work on interpretability in machine learning has focused on designi...

20 Gregory Plumb, et al. ∙

research

∙ 12/18/2018

Expanding the Reach of Federated Learning by Reducing Client Resource Requirements

Communication on heterogeneous edge networks is a fundamental bottleneck...

10 Sebastian Caldas, et al. ∙

research

∙ 12/14/2018

On the Convergence of Federated Optimization in Heterogeneous Networks

The burgeoning field of federated learning involves training machine lea...

0 Anit Kumar Sahu, et al. ∙

research

∙ 12/03/2018

LEAF: A Benchmark for Federated Settings

Modern federated networks, such as those comprised of wearable devices, ...

0 Sebastian Caldas, et al. ∙

research

∙ 10/13/2018

Massively Parallel Hyperparameter Tuning

Modern learning models are characterized by large hyperparameter spaces....

0 Liam Li, et al. ∙

research

∙ 07/09/2018

Supervised Local Modeling for Interpretability

Model interpretability is an increasingly important component of practic...

6 Gregory Plumb, et al. ∙

research

∙ 07/03/2017

Parle: parallelizing stochastic gradient descent

We propose a new algorithm called Parle for parallel training of deep ne...

0 Pratik Chaudhari, et al. ∙

research

∙ 05/30/2017

Federated Multi-Task Learning

Federated learning poses new statistical and systems challenges in train...

0 Virginia Smith, et al. ∙

research

∙ 03/21/2016

Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization

Performance of machine learning algorithms depends critically on identif...

0 Lisha Li, et al. ∙

research

∙ 05/26/2015

MLlib: Machine Learning in Apache Spark

Apache Spark is a popular open-source platform for large-scale data proc...

0 Xiangrui Meng, et al. ∙

Ameet Talwalkar

Featured Co-authors