Exact Diffusion for Distributed Optimization and Learning-Part I: Algorithm Development

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

paper studies exploiting action-level learning (imitation) in the optimal control problem context. Cost functions defined by the optimal control methods are similar to the goal-level learning (emulation) in animals. However, imitating the robot's or others ...

Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and dep ...

Inverse reconstruction from images is a central problem in many scientific and engineering disciplines. Recent progress on differentiable rendering has led to methods that can efficiently differentiate the full process of image formation with respect to mi ...

The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of O(ϵ-2) to achieve an ϵ-stationary solut ...

Astrobots are robotic artifacts whose swarms are used in astrophysical studies to generate the map of the observable universe. These swarms have to be coordinated with respect to various desired observations. Such coordination\footnote{\z{A coordination sa ...

Two-level domain decomposition methods are very powerful techniques for the efficient numerical solution of partial differential equations (PDEs). A two-level domain decomposition method requires two main components: a one-level preconditioner (or its corr ...

Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mismatch with typical speech. Unfortunately, these approaches rely on transcrib ...

Object detection, a fundamental task in computer vision, is crucial for various intelligent edge computing applications. However, object detection algorithms are usually heavy in computation, hindering their deployments on resource-constrained edge devices ...

We present a computational inverse design method for a new class of surface-based inflatable structure. Our deployable structures are fabricated by fusing together two layers of inextensible sheet material along carefully selected curves. The fusing curves ...

Photorealistic synthetic data and novel rendering techniques significantly advanced computer vision research. However, datasets focused on computer vision applications cannot be easily applied to robotics because they typically lack physics-related informa ...

We present a strikingly simple proof that two rules are sufficient to automate gradient descent: 1) don’t increase the stepsize too fast and 2) don’t overstep the local curvature. No need for functional values, no line search, no information about the func ...

A novel approach is introduced to determine the time evolution of optical forces and torques on arbitrary shape nanostructures by combining Maxwell's stress tensor with the surface integral equation method (SIE). Conventional time averaging of Maxwell’s st ...

Constant step-size Stochastic Gradient Descent exhibits two phases: a transient phase during which iterates make fast progress towards the optimum, followed by a stationary phase during which iterates oscillate around the optimal point. In this paper, we s ...

The objective of this thesis is to provide a mathematical and computational framework for the proactive maintenance of complex systems with a particular application to structural health monitoring (SHM). SHM techniques rely primarily on sensor responses to ...

This paper showcases the theoretical and numerical performance of the Sliding Frank-Wolfe, which is a novel optimization algorithm to solve the BLASSO sparse spikes super-resolution problem. The BLASSO is a continuous (i.e. off-the-grid or grid-less) count ...

Part I of this paper developed the exact diffusion algorithm to remove the bias that is characteristic of distributed solutions for deterministic optimization problems. The algorithm was shown to be applicable to the larger set of locally balanced left-sto ...

This paper considers a generic convex minimization template with affine constraints over a compact domain, which covers key semidefinite programming applications. The existing conditional gradient methods either do not apply to our template or are too slow ...

The contact of solids with rough surfaces plays a fundamental role in physical phenomena such as friction, wear, sealing, and thermal transfer. However, its simulation is a challenging problem due to surface asperities covering a wide range of length-scale ...

In this paper, we propose an algorithm to detect a specific kind of distortions, referred to as seams, which commonly occur when a 360-degree image is represented in planar domain by projecting the sphere to a polyhedron, e.g, via the Cube Map (CM) project ...

Direct simulation Monte-Carlo (DSMC) is the most established method for rarefied gas flow simulations. It is valid from continuum to near vacuum, but in cases involving small Knudsen numbers (Kn), it suffers from high computational cost. The Fokker-Planck ...

Exact Diffusion for Distributed Optimization and Learning-Part I: Algorithm Development

Chattez avec Graph Search

Optimal Control Combining Emulation and Imitation to Acquire Physical Assistance Skills

MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering

Large Steps in Inverse Rendering of Geometry

Diffusion Stochastic Optimization for Min-Max Problems

Data-Driven Convergence Prediction of Astrobots Swarms

Substructured Two-grid and Multi-grid Domain Decomposition Methods

Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR

Edge-Cloud Collaborated Object Detection via Bandwidth Adaptive Difficult-Case Discriminator

Computational Inverse Design of Surface-based Inflatables

GRADE: Generating Realistic and Dynamic Environments for robotics research with Isaac Sim

Adaptive Gradient Descent without Descent

Dynamics of optical forces and torques in plasmonic systems: a surface integral equation

On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent

Numerical methods for structural anomaly detection using model order reduction and data-driven techniques

The sliding Frank-Wolfe algorithm and its application to super-resolution microscopy

Exact Diffusion for Distributed Optimization and Learning-Part II: Convergence Analysis

A Conditional Gradient-Based Augmented Lagrangian Framework

A Fourier-accelerated volume integral method for elastoplastic contact

Graph-Based Detection of Seams In 360-Degree Images

Controlling the bias error of Fokker- Planck methods for rarefied gas dynamics simulations