Person

Sebastian Urban Stich

This person is no longer with EPFL

Related publications (26)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

, , ,

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when increasing the batc ...

2020

Ensemble Distillation for Robust Model Fusion in Federated Learning

Martin Jaggi, Sebastian Urban Stich, Tao Lin, Lingjing Kong

Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the par ...

2020

The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Updates

Sebastian Urban Stich, Sai Praneeth Reddy Karimireddy

We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-convex and non-convex functions and derive concise, non-asymptotic, convergence rates. We show that the rate of convergence in all cases consists of two terms: (i) a stocha ...

MICROTOME PUBL2020

, , ,

Coordinate descent with random coordinate selection is the current state of the art for many large scale optimization problems. However, greedy selection of the steepest coordinate on smooth problems can yield convergence rates independent of the dimension ...

2019

, , ,

MICROTOME PUBLISHING2019

Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication

Martin Jaggi, Sebastian Urban Stich, Anastasiia Koloskova

We consider decentralized stochastic optimization with the objective function (e.g. data samples for machine learning task) being distributed over n machines that can only communicate to their neighbors on a fixed communication graph. To reduce the communi ...

2019

Local SGD Converges Fast and Communicates Little

Sebastian Urban Stich

Mini-batch stochastic gradient descent (SGD) is state of the art in large scale distributed training. The scheme can reach a linear speedup with respect to the number of workers, but this is rarely seen in practice as the scheme often suffers from large ne ...

2019

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Martin Jaggi, Sebastian Urban Stich, Quentin Rebjock, Sai Praneeth Reddy Karimireddy

Sign-based algorithms (e.g. signSGD) have been proposed as a biased gradient compression technique to alleviate the communication bottleneck in training large neural networks across multiple workers. We show simple convex counter-examples where signSGD doe ...

PMLR2019

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Martin Jaggi, Sebastian Urban Stich, Quentin Rebjock, Sai Praneeth Reddy Karimireddy

2019

Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization

Sebastian Urban Stich

We present the first accelerated randomized algorithm for solving linear systems in Euclidean spaces. One essential problem of this type is the matrix inversion problem. In particular, our algorithm can be specialized to invert positive definite matrices i ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2018