Optimisation

Publication

Scaling Gaussian process optimization by evaluating a few unique candidates multiple times

Daniele Calandriello, Luigi Carratino *, Alessandro Lazaric *, Lorenzo Rosasco *, Michal Valko

ICML

Download

Publication

Online Apprenticeship Learning

Lior Shani *, Tom Zahavy, Shie Mannor *

AAAI

Download

Publication

Deep Kernel Shaping

James Martens, Andy Ballard, Guillaume Desjardins, Grzegorz Swirszcz, Valentin Dalibard, Jascha Sohl-Dickstein *, Sam Schoenholz *

arXiv

Download

Publication

Accelerated Forward-Backward Optimization using Deep Learning

Sebastian Banert *, Jevgenija Rudzusika *, Ozan Öktem *, Jonas Adler

arXiv

Download

Publication

Combinatorial optimization and reasoning with graph neural networks

Quentin Cappart *, Didier Chétalat *, Elias Khalil *, Andrea Lodi *, Christopher Morris *, Petar Veličković

IJCAI

Download

Publication

High-Performance Large-Scale Image Recognition Without Normalization

Andy Brock, Soham De, Sam Smith, Karen Simonyan

ICML

Download

Publication

Sampling from a k-DPP without looking at all items

Daniele Calandriello, Michal Dereziński *, Michal Valko

NeurIPS

Download

Publication

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Dj Dvijotham, Jonathan Uesato, Sumanth Dathathri, Rudy Bunel, Pushmeet Kohli

NeurIPS

Download

Publication

Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains

F Ruiz *, Michalis Titsias, Taylan Cemgil, Arnaud Doucet

arXiv

Download

Publication

A Simpler Approach to Accelerated Stochastic Optimization: Iterative Averaging Meets Optimism

Pooria Joulani, A Raj *, András György, Csaba Szepesvári

ICML

Download

Publication

On the generalization benefit of stochastic gradient descent

Samuel L. Smith, Erich Elsen, Soham De

ICML

Download

Publication

SOLA: Continual Learning with Second-Order Loss Approximation

Dong Yin, Mehrdad Farajtabar, Ang Li

arXiv

Download

Publication

Understanding the Role of Training Regimes in Continual Learning

Seyed-Iman Mirzadeh *, Mehrdad Farajtabar, Razvan Pascanu, Hassan Ghasemzadeh *

arXiv

Download

Publication

Discretization Drift in Two-Player Games

Mihaela Rosca, Yan Wu, Benoit Dherin *, David Barrett

ICML

Download

Publication

Stochastic Matrix Games with Bandit Feedback

Brendan O'Donoghue, Tor Lattimore, Ian Osband

arXiv

Download

Publication

A Distributional View on Multi-Objective Policy Optimization

Abbas Abdolmaleki, Sandy Huang, Leonard Hasenclever, Michael Neunert, Francis Song, Martina Zambelli, Murilo Martins, Nicolas Heess, Raia Hadsell, Martin Riedmiller

ICML

Download

Publication

On the Global Convergence Rates of Softmax Policy Gradient Methods

Jincheng Mei *, C Xiao *, Csaba Szepesvári, Dale Schuurmans *

ICML

Download

Publication

Dropout as an Implicit Gating Mechanism For Continual Learning

Seyed-Iman Mirzadeh *, Mehrdad Farajtabar, Hassan Ghasemzadeh *

arXiv

Download

Publication

Operator splitting for a homogeneous embedding of the monotone linear complementarity problem

Brendan O'Donoghue

arXiv

Download

Publication

Lagrangian Decomposition for Neural Network Verification

Rudy Bunel *, A De Palma *, Alban Desmaison *, Krishnamurthy (Dj) Dvijotham, Pushmeet Kohli, Philip Torr *, P Kumar *

arXiv

Download

Publication

Batch Normalization Biases Deep Residual Networks Towards Shallow Paths

Soham De, Samuel L. Smith

arXiv

Download

Publication

Self-Distillation Amplifies Regularization in Hilbert Space

Hossein Mobahi *, Mehrdad Farajtabar, Peter Bartlett *

arXiv

Download

Publication

On two ways to use determinantal point processes for Monte Carlo integration

Guillaume Gautier *, R Bardenet *, Michal Valko

NeurIPS

Download

Publication

LOGAN: Latent Optimisation for Generative Adversarial Networks

Yan Wu, Jeff Donahue, David Balduzzi, Karen Simonyan, Timothy Lillicrap

arXiv

Download

Publication

Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient

Kevin Sebastian Luck *, Mel Vecerik, S Stepputtis *, H B Amor *, Jonathan Scholz

arXiv

Download

Publications

Optimisation