Nicolas Loizou

is this you? claim profile

∙ 0 followers

PhD student at the University of Edinburgh

AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods

We present an adaptive stochastic variance reduced method with an implic...
02/19/2021 ∙ by Zheng Shi, et al. ∙ 12 ∙ share

read it
Stochastic Hamiltonian Gradient Methods for Smooth Games

The success of adversarial formulations in machine learning has brought ...
07/08/2020 ∙ by Nicolas Loizou, et al. ∙ 45 ∙ share

read it
Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization

We present a unified theorem for the convergence analysis of stochastic ...
06/20/2020 ∙ by Ahmed Khaled, et al. ∙ 30 ∙ share

read it
SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation

We provide several convergence theorems for SGD for two large classes of...
06/18/2020 ∙ by Robert M. Gower, et al. ∙ 17 ∙ share

read it
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates

Decentralized stochastic optimization methods have gained a lot of atten...
03/23/2020 ∙ by Anastasia Koloskova, et al. ∙ 0 ∙ share

read it
Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence

We propose a stochastic variant of the classical Polyak step-size (Polya...
02/24/2020 ∙ by Nicolas Loizou, et al. ∙ 13 ∙ share

read it
Randomized Iterative Methods for Linear Systems: Momentum, Inexactness and Gossip

In the era of big data, one of the key challenges is the development of ...
09/26/2019 ∙ by Nicolas Loizou, et al. ∙ 0 ∙ share

read it
Revisiting Randomized Gossip Algorithms: General Framework, Convergence Rates and Novel Block and Accelerated Protocols

In this work we present a new framework for the analysis and design of r...
05/20/2019 ∙ by Nicolas Loizou, et al. ∙ 0 ∙ share

read it
Convergence Analysis of Inexact Randomized Iterative Methods

In this paper we present a convergence rate analysis of inexact variants...
03/19/2019 ∙ by Nicolas Loizou, et al. ∙ 11 ∙ share

read it
SGD: General Analysis and Improved Rates

We propose a general yet simple theorem describing the convergence of SG...
01/27/2019 ∙ by Robert Mansel Gower, et al. ∙ 5 ∙ share

read it
A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion

In this work we present a randomized gossip algorithm for solving the av...
01/27/2019 ∙ by Filip Hanzely, et al. ∙ 0 ∙ share

read it
Stochastic Gradient Push for Distributed Deep Learning

Large mini-batch parallel SGD is commonly used for distributed training ...
11/27/2018 ∙ by Mahmoud Assran, et al. ∙ 0 ∙ share

read it
Provably Accelerated Randomized Gossip Algorithms

In this work we present novel provably accelerated gossip algorithms for...
10/31/2018 ∙ by Nicolas Loizou, et al. ∙ 0 ∙ share

read it
Accelerated Gossip via Stochastic Heavy Ball Method

In this paper we show how the stochastic heavy ball method (SHB) -- a po...
09/23/2018 ∙ by Nicolas Loizou, et al. ∙ 0 ∙ share

read it
Momentum and Stochastic Momentum for Stochastic Gradient, Newton, Proximal Point and Subspace Descent Methods

In this paper we study several classes of stochastic optimization algori...
12/27/2017 ∙ by Nicolas Loizou, et al. ∙ 0 ∙ share

read it
Linearly convergent stochastic heavy ball method for minimizing generalization error

In this work we establish the first linear convergence result for the st...
10/30/2017 ∙ by Nicolas Loizou, et al. ∙ 0 ∙ share

read it

Nicolas Loizou

Featured Co-authors

Peter Richtarik

Martin Jaggi

Simon Lacoste-Julien

Pascal Vincent

Martin Takáč

Ioannis Mitliagkas

Sebastian U. Stich

Nicolas Ballas

Michael Rabbat

Filip Hanzely

Jakub Konečný

AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods

Stochastic Hamiltonian Gradient Methods for Smooth Games

Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization

SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation

A Unified Theory of Decentralized SGD with Changing Topology and Local Updates

Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence

Randomized Iterative Methods for Linear Systems: Momentum, Inexactness and Gossip

Revisiting Randomized Gossip Algorithms: General Framework, Convergence Rates and Novel Block and Accelerated Protocols

Convergence Analysis of Inexact Randomized Iterative Methods

SGD: General Analysis and Improved Rates

A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion

Stochastic Gradient Push for Distributed Deep Learning

Provably Accelerated Randomized Gossip Algorithms

Accelerated Gossip via Stochastic Heavy Ball Method

Momentum and Stochastic Momentum for Stochastic Gradient, Newton, Proximal Point and Subspace Descent Methods

Linearly convergent stochastic heavy ball method for minimizing generalization error