Hassan Ashtiani

According to our database, Hassan Ashtiani authored at least 20 papers between 2015 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2023

Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity.

Alireza Fathollah Pour, Hassan Ashtiani, Shahab Asoodeh

CoRR, 2023

Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samples.

Mohammad Afzali, Hassan Ashtiani, Christopher Liaw

CoRR, 2023

On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences.

Alireza Fathollah Pour, Hassan Ashtiani

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models.

Jamil Arbas, Hassan Ashtiani, Christopher Liaw

Proceedings of the International Conference on Machine Learning, 2023

Adversarially Robust Learning with Tolerance.

Hassan Ashtiani, Vinayak Pathak, Ruth Urner

Proceedings of the International Conference on Algorithmic Learning Theory, 2023

2022

Benefits of Additive Noise in Composing Classes with Bounded Capacity.

Alireza Fathollah Pour, Hassan Ashtiani

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Private and polynomial time algorithms for learning Gaussians and beyond.

Hassan Ashtiani, Christopher Liaw

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

Privately Learning Mixtures of Axis-Aligned Gaussians.

Ishaq Aden-Ali, Hassan Ashtiani, Christopher Liaw

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians.

Ishaq Aden-Ali, Hassan Ashtiani, Gautam Kamath

Proceedings of the Algorithmic Learning Theory, 2021

2020

Near-optimal Sample Complexity Bounds for Robust Learning of Gaussian Mixtures via Compression Schemes.

Hassan Ashtiani, Shai Ben-David, Nicholas J. A. Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan

J. ACM, 2020

Black-box Certification and Learning under Adversarial Perturbations.

Hassan Ashtiani, Vinayak Pathak, Ruth Urner

Proceedings of the 37th International Conference on Machine Learning, 2020

On the Sample Complexity of Learning Sum-Product Networks.

Ishaq Aden-Ali, Hassan Ashtiani

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Disentangled behavioural representations.

Amir Dezfouli, Hassan Ashtiani, Omar Ghattas, Richard Nock, Peter Dayan, Cheng Soon Ong

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018

Some techniques in density estimation.

Hassan Ashtiani, Abbas Mehrabian

CoRR, 2018

Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes.

Hassan Ashtiani, Shai Ben-David, Nicholas J. A. Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Sample-Efficient Learning of Mixtures.

Hassan Ashtiani, Shai Ben-David, Abbas Mehrabian

Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017

Agnostic Distribution Learning via Compression.

Hassan Ashtiani, Shai Ben-David, Abbas Mehrabian

CoRR, 2017

2016

Clustering with Same-Cluster Queries.

Hassan Ashtiani, Shrinu Kushagra, Shai Ben-David

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

2015

Representation Learning for Clustering: A Statistical Framework.

Hassan Ashtiani, Shai Ben-David

Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 2015

A Dimension-Independent Generalization Bound for Kernel Supervised Principal Component Analysis.

Hassan Ashtiani, Ali Ghodsi

Proceedings of the 1st Workshop on Feature Extraction: Modern Questions and Challenges, 2015