Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs

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.

PSI and North Carolina State University are developing a high-resolution multi-physics core solver for Pressurized Water Reactor (PWR) analysis in Cartesian geometry, using the neutron transport code nTRACER and two Machine Learning (ML) models providing t ...

Visual grouping is the ability to combine parts of objects to form whole objects, and it is crucial for general and robust vision. Despite this, a comprehensive model of how the process works in humans remains elusive. In my thesis, I investigate how well ...

As urban populations continue to expand and vehicle density increases, the need for effective traffic monitoring and management becomes increasingly critical. Urban areas face significant challenges such as growing congestion, safety concerns, and parking ...

This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research has proposed vario ...

This chapter aims to provide a gentle introduction to Causal Learning (CL), and motivation for its application to medical image analysis, seeking for more robustness against data and domain drifts, and a reliable tool to answer counterfactual questions and ...

Conventional human trajectory prediction models rely on clean curated data, requiring specialized equipment or manual labeling, which is often impractical for robotic applications. The existing predictors tend to overfit to clean observation affecting thei ...

Deep neural networks (DNNs) provide state-of-the-art accuracy for vision tasks, but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increases communication ...

The ever-increasing demand for training and inferring with larger machine-learning models requires more efficient hardware solutions due to limitations such as power dissipation and scalability. Optics is a promising contender for providing lower power com ...

Methods of computational quantum chemistry provide accurate approximations of molecular properties crucial for computer-aided drug discovery and other areas of chemical science. However, high computational complexity limits the scalability of their applica ...

Graph neural network (GNN) models have presented astonishing achievements in various application fields. However, they are shown to be vulnerable to adversarial attacks on graph structure and unnoticeable perturbations on the graph structure can cause sign ...

With the advent of modern technologies for cryo-electron tomography (cryo-ET), high-quality tilt series are more rapidly acquired than processed and analyzed. Thus, a robust and fast-automated alignment for batch processing in cryo-ET is needed. While diff ...

Robust in-hand manipulation of objects with movable content requires estimation and prediction of the contents' motion with enough anticipation to allow time to compensate for resulting internal torques. The quick estimation of the objects' dynamics can be ...

Multi-pod systolic arrays are emerging as the architecture of choice in DNN inference accelerators. Despite their potential, designing multi-pod systolic arrays to maximize effective throughput/Watt-i.e., throughput/Watt adjusted when accounting for array ...

The process of quantifying and analyzing animal behavior involves translating the naturally occurring descriptive language of their actions into machine-readable code. Yet, codifying behavior analysis is often challenging without deep understanding of anim ...

The identification of nanomaterials with the properties required for energy-efficient electronic systems is usually a tedious human task. A workflow to rapidly localize and characterize nanomaterials at the various stages of their integration into large-sc ...

In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate how learning wi ...

Attention-based architectures have become ubiquitous in machine learning. Yet, our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their output can be de ...

Recently, deep networks have achieved impressive semantic segmentation performance, in particular thanks to their use of larger contextual information. In this paper, we show that the resulting networks are sensitive not only to global adversarial attacks, ...

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs

Chat with Graph Search

High-resolution predictions of the coolant properties for the 3D PWR core with artificial neural networks based on CTF

Differences in Visual Perception in Humans and Deep Neural Networks

Drone-Based Urban Traffic Monitoring and User Behavior Prediction

Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-training Strategies and Performance Insights

Causality: fundamental principles and tools

Unified Human Localization and Trajectory Prediction with Monocular Vision

Hierarchical Training of Deep Neural Networks Using Early Exiting

Programming nonlinear propagation for efficient optical learning machines

∇2DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials

A Joint Graph Signal and Laplacian Denoising Network

Automated fiducial-based alignment of cryo-electron tomography tilt series in Dynamo

A Predictive Model for Tactile Force Estimation Using Audio-Tactile Data

Scale-out Systolic Arrays

AmadeusGPT: a natural language interface for interactive animal behavioral analysis

High-speed identification of suspended carbon nanotubes using Raman spectroscopy and deep learning

Model-Agnostic Learning to Meta-Learn

Attention is not all you need: pure attention loses rank doubly exponentially with depth

Indirect Local Attacks for Context-aware Semantic Segmentation Networks