activity
20162023
most citedOrthogonal Gradient Descent for Continual Learning

39 citations · 90 across the 11 of their papers we have counts for

collaborators

15 papers

cs.CR2023

Private Synthetic Data Meets Ensemble Learning

Haoyuan Sun, Navid Azizan, Akash Srivastava +1

When machine learning models are trained on synthetic data and then deployed on real data, there is often a performance drop due to the distribution shift between synthetic and rea…

cs.LG20236 cited

Automatic Gradient Descent: Deep Learning without Hyperparameters

Jeremy Bernstein, Chris Mingard, Kevin Huang +2

The architecture of a deep neural network is defined explicitly in terms of the number of layers, the width of each layer and the general network topology. Existing optimisation fr…

eess.SY2023

Data-Driven Control with Inherent Lyapunov Stability

Youngjae Min, Spencer M. Richards, Navid Azizan

Recent advances in learning-based control leverage deep function approximators, such as neural networks, to model the evolution of controlled dynamical systems over time. However,…

cs.LG2022

Uncertainty in Contrastive Learning: On the Predictability of Downstream Performance

Shervin Ardeshir, Navid Azizan

The superior performance of some of today's state-of-the-art deep learning models is to some extent owed to extensive (self-)supervised contrastive pretraining on large-scale datas…

cs.RO2022

Control-oriented meta-learning

Spencer M. Richards, Navid Azizan, Jean-Jacques Slotine +1

Real-time adaptation is imperative to the control of robots operating in complex, dynamic environments. Adaptive control laws can endow even nonlinear systems with good trajectory…

cs.LG20221 cited

Online Learning for Traffic Routing under Unknown Preferences

Devansh Jalota, Karthik Gopalakrishnan, Navid Azizan +2

In transportation networks, users typically choose routes in a decentralized and self-interested manner to minimize their individual travel costs, which, in practice, often results…