Saddle-to-Saddle Dynamics in Diagonal Linear Networks

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.

Renewable energy resources have an increasing share of the electrical power, and the concept of distributed generation and storage units is about to completely change the basic architecture and control algorithms of the electric power grids. In this tutori ...

Convolutional neural networks perform a local and translationally-invariant treatment of the data: quantifying which of these two aspects is central to their success remains a challenge. We study this problem within a teacher-student framework for kernel r ...

A computer-implemented method for reconstructing/recovering high-resolution visible light spectral data at a target resolution d, that comprises obtaining a configuration of a low- resolution multi-channel imaging sensor of resolution p, the configuration ...

We study 1D continuous-domain inverse problems for multicomponent signals. The prior assumption on these signals is that each component is sparse in a different dictionary specified by a regularization operators. We introduce a hybrid regularization functi ...

Multiple generalized additive models are a class of statistical regression models wherein parameters of probability distributions incorporate information through additive smooth functions of predictors. The functions are represented by basis function expan ...

Neural-network quantum states (NQS) have been shown to be a suitable variational ansatz to simulate out-of-equilibrium dynamics in two-dimensional systems using timedependent variational Monte Carlo (t-VMC). In particular, stable and accurate time propagat ...

We consider a least-squares/relaxation finite element method for the numerical solution of the prescribed Jacobian equation. We look for its solution via a least-squares approach. We introduce a relaxation algorithm that decouples this least-squares proble ...

We study continuous-domain linear inverse problems with generalized total-variation (gTV) regularization, expressed in terms of a regularization operator L. It has recently been proved that such inverse problems have sparse spline solutions, with fewer jum ...

In this paper, we study regression problems over a separable Hilbert space with the square loss, covering non-parametric regression over a reproducing kernel Hilbert space. We investigate a class of spectral/regularized algorithms, including ridge regressi ...

The scale of modern datasets necessitates the development of efficient distributed optimization methods for machine learning. We present a general-purpose framework for distributed computing environments, CoCoA, that has an efficient communication scheme a ...

In this article, we address the numerical solution of the Dirichlet problem for the three-dimensional elliptic Monge-Ampere equation using a least-squares/relaxation approach. The relaxation algorithm allows the decoupling of the differential operators fro ...

Due to the rapid growth of data and computational resources, distributed optimization has become an active research area in recent years. While first-order methods seem to dominate the field, second-order methods are nevertheless attractive as they potenti ...

Digitization and preservation of large heritage induce high maintenance costs to keep up with the technical standards and ensure sustainable access. Creating impactful usage is instrumental to justify the resources for long-term preservation. The Museum fü ...

Several distributed-optimization setups involve a group of agents coordinated by a central entity (coordinator), altogether operating in a collaborative framework. In such environments, it is often common that the agents solve proximal minimization problem ...

We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial loss functions under different adversarial budgets. We then demonstrate tha ...

We propose a way to estimate the value function of a convex proximal minimization problem. The scheme constructs a convex set within which the optimizer resides and iteratively refines the set every time that the value function is sampled, namely every tim ...

In this paper, we propose a multi-fidelity approach for parameter estimation problems based on Physics-Informed Neural Networks (PINNs). The proposed methods apply to models expressed by linear or nonlinear differential equations, whose parameters need to ...

Optical tomography has been widely investigated for biomedical imaging applications. In recent years, it has been combined with digital holography and has been employed to produce high quality images of phase objects such as cells. In this Thesis, we look ...

Multi-objective gradient methods are becoming the standard for solving multi-objective problems. Among others, they show promising results in developing multi-objective recommender systems with both correlated and conflicting objectives. Classic multi-grad ...

Machine learning promises to accelerate materials discovery by allowing computational efficient property predictions from a small number of reference calculations. As a result, the literature spent a considerable effort in designing representations that ca ...

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

Chat with Graph Search

Data-Driven Control and Its Applications to Microgrids

Locality defeats the curse of dimensionality in convolutional teacher-student scenarios*

System and method for transcoding spectral data with task-based optimization via symmetric non-negative matrix factorization

Sparse Dictionaries for Continuous-Domain Inverse Problems

Automatic L2 Regularization for Multiple Generalized Additive Models

Role of stochastic noise and generalization error in the time propagation of neural-network quantum states

A Least-Squares Method for the Solution of the Non-smooth Prescribed Jacobian Equation

B-Spline-Based Exact Discretization of Continuous-Domain Inverse Problems With Generalized TV Regularization

Optimal Rates for Spectral Algorithms with Least-Squares Regression over Hilbert Spaces

CoCoA: A General Framework for Communication-Efficient Distributed Optimization

A Least-Squares/Relaxation Method for the Numerical Solution of the Three-Dimensional Elliptic Monge-Ampere Equation

A Distributed Second-Order Algorithm You Can Trust

Automatic Content Curation of Visual Heritage

Learning Proximal Operators with Gaussian Processes

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

A coordinator-driven communication reduction scheme for distributed optimization using the projected gradient method

Numerical Analysis - A physics-informed multi-fidelity approach for the estimation of differential equations parameters in low-data or large-noise regimes

3D Reconstruction of Optical Diffraction Tomography Based on a Neural Network Model

Momentum-based Gradient Methods in Multi-Objective Recommendation

Chemical machine learning with kernels: The key impact of loss functions