Amartya Sanyal

I will be starting as Assistant Professor in Machine Learning in the Department of Computer Science in University of Copenhagen from Summer, 2024 and will also be an Affiliated Assistant Professor in the Department of Mathematics.

Email / GitHub / Google Scholar / CV

Till then, I am a postdoctoral fellow at the Empirical Inference group in Max Planck Institute for Intelligent Systems, Tubingen where I work closely with Prof. Bernhard Schölkopf . Prior to this, I was a postdoctoral fellow at ETH Zurich AI Center where I worked closely with Prof. Fanny Yang . I completed my DPhil (PhD) at the Department of Computer Science, University of Oxford, funded by the Turing Doctoral Studentship. I was also a member of the Torr Vision Group. My DPhil advisors were Varun Kanade and Philip H.S. Torr. I am also a member of the ELLIS Society.

Prior to that, I completed my undergraduate (B.Tech in Computer Science) at the Indian Institute of Technology, Kanpur. On various occassions, I have spent time at Facebook AI Research (FAIR), Twitter Cortex , Laboratory for Computational and Statistical Learning, Montreal Institute of Learning Algorithms , and Amazon ML.

Job Advertisement

If you are interested in a PhD position with me, see here for more details

Research Interests

I am interested in understanding both theoretical and empirical aspects of Trustworthy Machine Learning including privacy, robustness, fairness. In particular, I am focusing on the impacts that inadequate data and computation may have on the trustworthiness of ML algorithms, especially under adversarial settings, and how one can solve these issues with reasonable approximations and relaxations including semi-supervised and self-supervised learning.

Current Students

I am very lucky to be currently working with the following students.

Prof. Bernhard Schölkopf

Prof. Fanny Yang

Upcoming/Recent Talks

MIT Algorithmic Fairness Seminar September 29	Fairness and Privacy in Machine Learning: Challenges in Long-Tailed Data and Innovations in Semi-Private Algorithms
University of Michigan Data Science Seminar October 04	Harnessing Low Dimensionality and public unlabelled data in Semi-Private Machine Learning Algorithms
CISPA Helmholtz Center for Information Security November 28	Harnessing Low Dimensionality and public unlabelled data in Semi-Private Machine Learning Algorithms

Recent News

April, 2024	I received a NNF Start Package grant. I am hiring a PhD student to start this fall . I will also be hiring a Postdoc. Email me if you think you would be great match.
February, 2024	Three new preprints: on the problem of separation between non-private and private online learning, privacy guarantees despite non-private pre-processing and machine unlearning beyond privacy concerns are online.
January, 2024	Our paper titled Sample-efficient private data release for Lipschitz functions under sparsity assumptions is accepted at AISTATS 2024.
December, 2023	Our paper PILLAR: How to make semi-private learning more effective on semi-private learning is accepted in SatML 2023 .
September, 2023	Our paper on understanding the capabilities of semi-supervised learning was accepted as a spotlight paper in NeurIPS 2023.
August, 2023	Two papers on i) leveraging small amounts of unlabelled public data for differentially private learning and ii) certified private data release were accepted in TPDP 2023
July, 2023	Our paper titled Catastrophic overfitting can be induced with discriminative non-robust features is accepted at TMLR .
April, 2023	Our paper titled Certifying Ensembles: A General Certification Theory with S-Lipschitzness is accepted at ICML 2023.
April, 2023	Co-organising the Workshop on Pitfalls of limited data and computation for Trustworthy ML at ICLR 2023 in Kigali, Rwanda.
January, 2023	Selected to speak at the Rising Stars in AI Symposium, 2023 in KAUST.
January, 2023	Two papers on i) interpolating label noise provably hurts adversarial robustness and ii) robustness of unsupervised representation learning to distribution shift were accepted in ICLR 2023

Publications

*Arxiv, 2024*	Provable Privacy with Non-Private Pre-Processing Yaxi Hu, Amartya Sanyal , Bernhard Schölkopf Arxiv, 2024 Arxiv /
*Arxiv, 2024*	On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective Daniil Dmitriev, Kristóf Szabó, Amartya Sanyal Arxiv, 2024 Arxiv /
*Arxiv, 2024*	Corrective Machine Unlearning Shashwat Goel, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru, Amartya Sanyal Arxiv, 2024 Arxiv /
*TPDP, AISTATS, 2024*	Certified private data release for sparse Lipschitz functions Konstantin Donhauser, Johan Lokna, Amartya Sanyal , March Boedihardjo, Robert Hönig, Fanny Yang, Artificial Intelligence and Statistics Theory and Practice of Differential Privacy , 2024 Arxiv /
NeurIPS, 2023 Spotlight Paper	Can semi-supervised learning use all the data effectively? A lower bound perspective Gizem Yüce* , Alexandru Țifrea , Amartya Sanyal , Fanny Yang Advances in Neural Information Processing Systems, 2023 Spotlight Paper Arxiv / Proceedings /
*TPDP, SaTML, 2023*	PILLAR: How to make semi-private learning more effective Francesco Pinto, Yaxi Hu, Fanny Yang, Amartya Sanyal IEEE Conference on Secure and Trustworthy Machine Learning Theory and Practice of Differential Privacy Workshop on Pitfalls of limited data and computation for Trustworthy ML , 2023 Arxiv / Proceedings / code / poster /
*TMLR, 2023*	Catastrophic overfitting can be induced with discriminative non-robust features Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal , Adel Bibi, Puneet Dokania, Pascal Frossard, Gregory Rogéz, Philip H.S. Torr TMLR , 2023 Arxiv / code /
*ICML, 2023*	Certifying Ensembles: A General Certification Theory with S-Lipschitzness Aleksandar Petrov, Francisco Eiras, Amartya Sanyal , Philip H.S. Torr, Adel Bibi International Conference on Machine Learning , 2023 Arxiv /
NeurIPS Workshop, 2023 Oral Paper	How robust accuracy suffers from certified training with convex relaxations Piersilvio De Bartolomeis, Jacob Clarysse, Fanny Yang, Amartya Sanyal Workshop on Understanding Deep Learning Through Empirical Falsification , 2023 Oral Paper Arxiv / Proceedings /
*Preprint, 2023*	Towards Adversarial Evaluations for Inexact Machine Unlearning Shashwat Goel, Ameya Prabhu, Amartya Sanyal , Ser-Nam Lim, Philip Torr, Ponnurangam Kumaraguru Arxiv, 2023 Arxiv /
*ICLR, 2023*	A law of adversarial risk, interpolation, and label noise Daniel Paleka, Amartya Sanyal International Conference on Learning Representations (ICLR), 2023 Arxiv / Proceedings / poster /
*ICLR, 2023*	How robust is unsupervised representation learning to distribution shift? Yuge Shi, Imant Daunhawer, Julia E. Vogt, Philip H.S. Torr , Amartya Sanyal . International Conference on Learning Representations (ICLR), 2023 Arxiv / Proceedings /
*NeurIPS, 2022*	Make Some Noise: Reliable and Efficient Single-Step Adversarial Training Pau De Jorge Aranda, Adel Bibi , Ricardo Volpi, Amartya Sanyal , Philip H.S. Torr, Grégory Rogez , Puneet Dokania Neural Information Processing Systems (NeurIPS) 2022., 2022 Arxiv / Proceedings /
UAI, 2022 Oral Paper	How unfair is private learning ? Amartya Sanyal , Yaxi Hu, Fanny Yang Conference on Uncertainty in Artificial Intelligence (UAI) , 2022 Oral Paper Arxiv / Proceedings / poster / slides /
*COLT, 2022*	Open Problem: Do you pay for Privacy in Online Learning ? Amartya Sanyal , Giorgia Ramponi Conference on Learning Theory (COLT) Open Problems, 2022 Arxiv / Proceedings / slides /
ICLR, 2021 Spotlight Paper	How benign is benign overfitting? Amartya Sanyal , Varun Kanade, Puneet Dokania, Philip H.S. Torr International Conference of Learning Representations (ICLR) , 2021 Spotlight Paper Arxiv / Proceedings / poster /
*ICLR, 2021*	Progressive Skeletonization: Trimming more fat from a network at initialization Pau De Jorge Aranda, Amartya Sanyal , Harkirat Behl , Philip H.S. Torr, Grégory Rogez , Puneet Dokania International Conference of Learning Representations (ICLR), 2021 Arxiv / Proceedings / code /
*NeurIPS, 2020*	Calibrating Deep Neural Networks using Focal Loss Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal , Stuart Golodetz, Philip H.S. Torr, Puneet Dokania Advances in Neural Information Processing Systems (NeurIPS), 2020 Arxiv / Proceedings / code /
ICLR, 2020 Spotlight Paper	Stable Rank Normalization for Improved Generalization in Neural Networks and GANs Amartya Sanyal , Philip H.S. Torr, Puneet Dokania International Conference of Learning Representations (ICLR), 2020 Spotlight Paper Arxiv / Proceedings / video /
*Preprint, 2019*	Robustness via Deep Low-Rank Representations Amartya Sanyal , Varun Kanade, Philip H.S. Torr, Puneet Dokania Preprint, 2019 Arxiv /
*ICML, 2018*	TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service Amartya Sanyal , Matt Kusner , Adrià Gascón Varun Kanade International Conference of Machine Learning (ICML), 2018 Arxiv / Proceedings / code /
*ICML Workshop, 2017*	Multiscale sequence modeling with a learned dictionary Bart van Merriënboer, Amartya Sanyal , Hugo Larochelle, Yoshua Bengio Machine Learning in Speech and Language Processing, 2017 Arxiv /

Design and source code from Jon Barron's website

Amartya Sanyal

Job Advertisement

Research Interests

Current Students

Upcoming/Recent Talks

Recent News

April, 2024

I received a NNF Start Package grant. I am hiring a PhD student to start this fall . I will also be hiring a Postdoc. Email me if you think you would be great match.

February, 2024

Three new preprints: on the problem of separation between non-private and private online learning, privacy guarantees despite non-private pre-processing and machine unlearning beyond privacy concerns are online.

January, 2024

Our paper titled Sample-efficient private data release for Lipschitz functions under sparsity assumptions is accepted at AISTATS 2024.

December, 2023

Our paper PILLAR: How to make semi-private learning more effective on semi-private learning is accepted in SatML 2023 .

September, 2023

Our paper on understanding the capabilities of semi-supervised learning was accepted as a spotlight paper in NeurIPS 2023.

August, 2023

Two papers on i) leveraging small amounts of unlabelled public data for differentially private learning and ii) certified private data release were accepted in TPDP 2023

July, 2023

Our paper titled Catastrophic overfitting can be induced with discriminative non-robust features is accepted at TMLR .

April, 2023

Our paper titled Certifying Ensembles: A General Certification Theory with S-Lipschitzness is accepted at ICML 2023.

April, 2023

Co-organising the Workshop on Pitfalls of limited data and computation for Trustworthy ML at ICLR 2023 in Kigali, Rwanda.

January, 2023

Selected to speak at the Rising Stars in AI Symposium, 2023 in KAUST.

January, 2023

Two papers on i) interpolating label noise provably hurts adversarial robustness and ii) robustness of unsupervised representation learning to distribution shift were accepted in ICLR 2023

Publications

Provable Privacy with Non-Private Pre-Processing

On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective

Corrective Machine Unlearning

Certified private data release for sparse Lipschitz functions

Can semi-supervised learning use all the data effectively? A lower bound perspective

PILLAR: How to make semi-private learning more effective

Catastrophic overfitting can be induced with discriminative non-robust features

Certifying Ensembles: A General Certification Theory with S-Lipschitzness

How robust accuracy suffers from certified training with convex relaxations

Towards Adversarial Evaluations for Inexact Machine Unlearning

A law of adversarial risk, interpolation, and label noise

How robust is unsupervised representation learning to distribution shift?

Make Some Noise: Reliable and Efficient Single-Step Adversarial Training

How unfair is private learning ?

Open Problem: Do you pay for Privacy in Online Learning ?

How benign is benign overfitting?

Progressive Skeletonization: Trimming more fat from a network at initialization

Calibrating Deep Neural Networks using Focal Loss

Stable Rank Normalization for Improved Generalization in Neural Networks and GANs

Robustness via Deep Low-Rank Representations

TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service

Multiscale sequence modeling with a learned dictionary