Alireza Fathollah Pour

According to our database, Alireza Fathollah Pour authored at least 3 papers between 2022 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

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

Alireza Fathollah Pour, Hassan Ashtiani, Shahab Asoodeh

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

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

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