12 citations · 17 across the 3 of their papers we have counts for
6 papers
An Elementary Approach to Convergence Guarantees of Optimization Algorithms for Deep Networks
Vincent Roulet, Zaid Harchaoui
We present an approach to obtain convergence guarantees of optimization algorithms for deep networks based on elementary arguments and computations. The convergence analysis revolv…
On the Convergence of the Iterative Linear Exponential Quadratic Gaussian Algorithm to Stationary Points
Vincent Roulet, Maryam Fazel, Siddhartha Srinivasa +1
A classical method for risk-sensitive nonlinear control is the iterative linear exponential quadratic Gaussian algorithm. We present its convergence analysis from a first-order opt…
Iterative Linearized Control: Stable Algorithms and Complexity Guarantees
Vincent Roulet, Siddhartha Srinivasa, Dmitriy Drusvyatskiy +1
We examine popular gradient-based algorithms for nonlinear control in the light of the modern complexity analysis of first-order optimization algorithms. The examination reveals th…
Kernel-based Translations of Convolutional Networks
Corinne Jones, Vincent Roulet, Zaid Harchaoui
Convolutional Neural Networks, as most artificial neural networks, are commonly viewed as methods different in essence from kernel-based methods. We provide a systematic translatio…
A Smoother Way to Train Structured Prediction Models
Krishna Pillutla, Vincent Roulet, Sham M. Kakade +1
We present a framework to train a structured prediction model by performing smoothing on the inference algorithm it builds upon. Smoothing overcomes the non-smoothness inherent to…
Integration Methods and Accelerated Optimization Algorithms
Damien Scieur, Vincent Roulet, Francis Bach +1
We show that accelerated optimization methods can be seen as particular instances of multi-step integration schemes from numerical analysis, applied to the gradient flow equation.…