activity
20182024
most citedChaining Mutual Information and Tightening Generalization Bounds

13 citations · 31 across the 7 of their papers we have counts for

collaborators

7 papers

cs.HC2024

Towards Mixed Reality as the Everyday Computing Paradigm: Challenges & Design Recommendations

Amir Reza Asadi, Reza Hemadi

This research presents a proof-of-concept prototype of an all-in-one mixed reality application platform, developed to investigate the needs and expectations of users from mixed rea…

stat.ML2023

An Entropy-Based Model for Hierarchical Learning

Amir R. Asadi

Machine learning is the dominant approach to artificial intelligence, through which computers learn from data and experience. In the framework of supervised learning, a necessity f…

cs.CY2022★ 9 cited

Understanding Currencies in Video Games: A Review

Amir Reza Asadi, Reza Hemadi

This paper presents a review of the status of currencies in video games. The business of video games is a multibillion-dollar industry, and its internal economy design is an import…

cs.AI2022★ 8 cited

Cognitive Ledger Project: Towards Building Personal Digital Twins Through Cognitive Blockchain

Amir Reza Asadi

The Cognitive Ledger Project is an effort to develop a modular system for turning users' personal data into structured information and machine learning models based on a blockchain…

cs.LG2020

Maximum Multiscale Entropy and Neural Network Regularization

Amir R. Asadi, Emmanuel Abbe

A well-known result across information theory, machine learning, and statistical physics shows that the maximum entropy distribution under a mean constraint has an exponential form…

cs.LG2019★ 1 cited

Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets

Amir R. Asadi, Emmanuel Abbe

We derive generalization and excess risk bounds for neural nets using a family of complexity measures based on a multilevel relative entropy. The bounds are obtained by introducing…

cs.LG2018★ 13 cited

Chaining Mutual Information and Tightening Generalization Bounds

Amir R. Asadi, Emmanuel Abbe, Sergio Verdú

Bounding the generalization error of learning algorithms has a long history, which yet falls short in explaining various generalization successes including those of deep learning.…