Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances. ICLR 2024.

Mikhail Khodak, Edmond Chow, Maria-Florina Balcan, Ameet Talwalkar.
[paper] [arXiv] [code] [poster]

Meta-Learning Adversarial Bandit Algorithms. NeurIPS 2023.

Mikhail Khodak*, Ilya Osadchiy*, Keegan Harris, Maria-Florina Balcan, Kfir Y. Levy, Ron Meir, Zhiwei Steven Wu.
[paper] [arXiv]

Learning-Augmented Private Algorithms for Multiple Quantile Release. ICML 2023.

Mikhail Khodak, Kareem Amin, Travis Dick, Sergei Vassilvitskii.
[paper] [arXiv] [code]

Cross-Modal Fine-Tuning: Align then Refine. ICML 2023.

Junhong Shen, Liam Li, Lucio M. Dery, Corey Staten, Mikhail Khodak, Graham Neubig, Ameet Talwalkar.
[paper] [arXiv] [code] [slides]

On Noisy Evaluation in Federated Hyperparameter Tuning. MLSys 2023.

Kevin Kuo, Pratiksha Thaker, Mikhail Khodak, John Nguyen, Daniel Jiang, Ameet Talwalkar, Virginia Smith.
[paper] [arXiv] [blog]

Meta-Learning in Games. ICLR 2023.

Keegan Harris*, Ioannis Anagnostides*, Gabriele Farina, Mikhail Khodak, Zhiwei Steven Wu, Tuomas Sandholm.
[paper] [arXiv]

AANG: Automating Auxiliary Learning. ICLR 2023.

Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar.
[paper] [arXiv] [code]

Provably Tuning the ElasticNet Across Instances. NeurIPS 2022.

Maria-Florina Balcan, Mikhail Khodak, Dravyansh Sharma, Ameet Talwalkar.
[paper] [arXiv] [blog] [talk]

Efficient Architecture Search for Diverse Tasks. NeurIPS 2022.

Junhong Shen*, Mikhail Khodak*, Ameet Talwalkar.
[paper] [arXiv] [slides] [code] [blog]

Learning Predictions for Algorithms with Predictions. NeurIPS 2022.

Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar, Sergei Vassilvitskii.
[paper] [arXiv] [poster] [talk]

NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks. NeurIPS 2022 (Datasets and Benchmarks Track).

Renbo Tu*, Nicholas Roberts*, Mikhail Khodak, Junhong Shen, Frederic Sala, Ameet Talwalkar.
[paper] [arXiv] [code] [website]

A Deeper Look at Zero-Cost Proxies for Lightweight NAS. ICLR 2022 (Blog Track).

Colin White, Mikhail Khodak, Renbo Tu, Shital Shah, Sébastien Bubeck, Debadeepta Dey.
[post]

Rethinking Neural Operations for Diverse Tasks. NeurIPS 2021.

Nicholas Roberts*, Mikhail Khodak*, Tri Dao, Liam Li, Christopher Ré, Ameet Talwalkar.
[paper] [arXiv] [code] [slides] [talk] [Python package]

Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing. NeurIPS 2021.

Mikhail Khodak, Renbo Tu, Tian Li, Liam Li, Maria-Florina Balcan, Virginia Smith, Ameet Talwalkar.
[paper] [arXiv] [code] [poster] [slides] [talk]

Learning-to-Learn Non-Convex Piecewise-Lipschitz Functions. NeurIPS 2021.

Maria-Florina Balcan, Mikhail Khodak, Dravyansh Sharma, Ameet Talwalkar.
[paper] [arXiv]

Geometry-Aware Gradient Algorithms for Neural Architecture Search. ICLR 2021.

Liam Li*, Mikhail Khodak*, Maria-Florina Balcan, Ameet Talwalkar.
[paper] [arXiv] [slides] [code] [blog] [talk] [Determined]

Initialization and Regularization of Factorized Neural Layers. ICLR 2021.

Mikhail Khodak, Neil Tenenholtz, Lester Mackey, Nicolò Fusi.
[paper] [arXiv] [code] [blog] [talk]

A Sample Complexity Separation between Non-Convex and Convex Meta-Learning. ICML 2020.

Nikunj Saunshi, Yi Zhang, Mikhail Khodak, Sanjeev Arora.
[paper] [arXiv] [talk]

Differentially Private Meta-Learning. ICLR 2020.

Jeffrey Li, Mikhail Khodak, Sebastian Caldas, Ameet Talwalkar.
[paper] [arXiv] [slides]

Adaptive Gradient-Based Meta-Learning Methods. NeurIPS 2019.

Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar.
[paper] [arXiv] [poster] [slides] [code] [blog] [talk]

A Theoretical Analysis of Contrastive Unsupervised Representation Learning. ICML 2019.

Sanjeev Arora, Hrishikesh Khandeparkar, Mikhail Khodak, Orestis Plevrakis, Nikunj Saunshi.
[paper] [arXiv] [poster] [slides] [data] [blog] [talk]

Provable Guarantees for Gradient-Based Meta-Learning. ICML 2019.

Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar.
[paper] [arXiv] [poster] [code] [data]

A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. ACL 2018.

Mikhail Khodak*, Nikunj Saunshi*, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora.
[paper] [arXiv] [slides] [code] [data] [blog] [talk] [R package]

A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs. ICLR 2018.

Sanjeev Arora, Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli.
[paper] [poster] [slides] [code] [data] [blog]

A Large Self-Annotated Corpus for Sarcasm. LREC 2018.

Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli.
[paper] [arXiv] [code] [data] [CBC] [Quartz] [The Register]

Learning Cloud Dynamics to Optimize Spot Instance Bidding Strategies. INFOCOM 2018.

Mikhail Khodak, Liang Zheng, Andrew S. Lan, Carlee Joe-Wong, Mung Chiang.
[paper] [supplement] [slides]