Elad Hazan: Efficient Optimization for Machine Learning: Beyond Stochastic Gradient Descent

Channel:
United States QuICS
Subscribers:
2,450
Published on ● Video Link: https://www.youtube.com/watch?v=AbM5JjcRLEk


Duration: 56:45
1,303 views
0

A talk by Elad Hazan at the Quantum Machine Learning Workshop, hosted September 24-28, 2018 by the Joint Center for Quantum Information and Computer Science at the University of Maryland (QuICS).

Abstract: In this talk we will describe recent advances in optimization that gave rise to state-of-the-art algorithms in machine learning. While stochastic gradient descent is the workhorse behind the recent deep learning revolution, improving its performance both theoretically and in practice has proven challenging. We will explore recent innovations in stochastic second order methods and adaptive regularization that yield some of the fastest algorithms known.



Other Videos By QuICS


2018-10-31Norbert Linke: Quantum Machine Learning with Trapped Ions
2018-10-31Kristan Temme: Supervised Learning with Quantum Enhanced Feature Spaces
2018-10-31Soheil Feizi: Generative Adversarial Networks: Formulation, Design and Computation
2018-10-31Nathan Wiebe: Optimizing Quantum Optimization Algorithms via Faster Quantum Gradient Computation
2018-10-31Rolando Somma: Quantum Algorithms for Systems of Linear Equations
2018-10-31Anupam Praksah: A Quantum Interior Point Method for LPs and SDPs
2018-10-31Furong Huang: Discovery of Latent Factors in High-dimensional Data Using Tensor Methods
2018-10-31Fernando Brandao: Quantum Speed-up for SDPs and Kernel Learning
2018-10-31Srinivasan Arunachalam: Strengths and weaknesses of quantum examples for learning
2018-10-31Vedran Dunjko: A Route towards Quantum-Enhanced Artificial Intelligence
2018-10-31Elad Hazan: Efficient Optimization for Machine Learning: Beyond Stochastic Gradient Descent
2017-10-11John Preskill: QEC in 2017β€”Past, present, and future
2017-10-11Sepehr Nezami: Quantum Error Correction of Reference Frame Information
2017-10-11Anirudh Krishna: Performance of hyperbolic surface codes
2017-10-11Brian Swingle: Entanglement, Wormholes, and Quantum Error Correction
2017-10-11Christa Flühmann: Preparation of Grid state qubits by sequential modular position measurements
2017-10-11Matteo Marinelli: Repetitive stabilizer readout with conditional feedback
2017-10-11Norbert Linke: Fault-tolerant quantum error detection with trapped ions
2017-10-11Rui Chao: Fault-tolerant quantum computation with few qubits
2017-10-11Michel Kastoryano: Limits on storage of quantum information in a volume of space
2017-10-11Fernando Pastawski: Towards holography via quantum source-channel codes


Tags:
machine learning
optimization