NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization

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.

We consider the problem of computing mixed Nash equilibria of two-player zero-sum games with continuous sets of pure strategies and with first-order access to the payoff function. This problem arises for example in game-theory-inspired machine learning app ...

Researchers have invested much effort into developing kinetic models due to their ability to capture dynamic behaviors, transient states, and regulatory mechanisms of metabolism, providing a detailed and realistic representation of cellular processes. Hist ...

Robotic welding envisioned for the future of factories will promote high-demanding and customised tasks with overall higher productivity and quality. Within the context, robotic welding parameter prediction is essential for maintaining high standards of qu ...

Natural aerosol components such as particulate methanesulfonic acid (MSA p) play an important role in the Arctic climate. However, numerical models struggle to reproduce MSA p concentrations and seasonality. Here we present an alternative data-driven metho ...

Evaluating the visual quality of distorted images is a crucial task in the field of image compression, as artifacts may significantly impair the appeal and fidelity of images, therefore reducing the user experience. As assessing the visual quality of image ...

The recent rise in interest in point clouds as an imaging modality has motivated standardization groups such as JPEG and MPEG to launch activities aiming at developing compression standards for point clouds. Lossy compression usually introduces visual arti ...

MapPool is a dataset of 75 million potential maps and textual captions. It has been derived from CommonPool, a dataset consisting of 12 billion text-image pairs from the Internet. The images have been encoded by a vision transformer and classified into map ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

Biohybrid systems in which robotic lures interact with animals have become compelling tools for probing and identifying the mechanisms underlying collective animal behavior. One key challenge lies in the transfer of social interaction models from simulatio ...

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

In this paper, we propose a novel adaptive feedforward super-twisting sliding mode control algorithm to resolve the tracking control problem of parallel manipulators. The proposed control scheme includes three main terms, (i) the standard super-twisting al ...

Including friction modeling in simulation can be challenging and requires time domain simulation, which is time consuming. We propose to separate the friction modelling from the FEA (Finite Element Analysis). The approach is defined for UCM (Ultrasonic Cer ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization

Chat with Graph Search

An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games

The Dawn of High-throughput and Genome-scale Kinetic Modeling: Recent Advances and Future Directions

Transfer learning and augmented data-driven parameter prediction for robotic welding

Data-driven modeling of environmental factors influencing Arctic methanesulfonic acid aerosol concentrations

Benchmarking conventional and learning-based objective image quality metrics on compression artifacts

Subjective performance evaluation of bitrate allocation strategies for MPEG and JPEG Pleno point cloud compression

MapPool -Bubbling up an extremely large corpus of maps for AI

Topics in statistical physics of high-dimensional machine learning

Quantifying the biomimicry gap in biohybrid robot-fish pairs

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Enabling Uncertainty Estimation in Iterative Neural Networks

Random matrix methods for high-dimensional machine learning models

Aggregating Spatial and Photometric Context for Photometric Stereo

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Adaptive Feedforward Super-Twisting Sliding Mode Control of Parallel Kinematic Manipulators With Real-Time Experiments

Contact Tip Trajectory in Steady-State Regime Prediction Using Deep Learning for Piezoelectric Actuators

Machine Learning for Modeling Stock Returns