Concept

Critical point (mathematics)

Related publications (49)

The effect of smooth parametrizations on nonconvex optimization landscapes

We develop new tools to study landscapes in nonconvex optimization. Given one optimization problem, we pair it with another by smoothly parametrizing the domain. This is either for practical purposes (e.g., to use smooth optimization algorithms with good g ...

Springer Heidelberg2024

Photothermal spectroscopy on-chip sensor for the measurement of a PMMA film using a silicon nitride micro-ring resonator and an external cavity quantum cascade laser

Simone Iadanza

Laser-based mid-infrared (mid-IR) photothermal spectroscopy (PTS) represents a selective, fast, and sensitive analytical technique. Recent developments in laser design permits the coverage of wider spectral regions in combination with higher power, enablin ...

Berlin2024

Avoidance of Concave Obstacles Through Rotation of Nonlinear Dynamics

Aude Billard, Lukas Huber

Controlling complex tasks in robotic systems, such as circular motion for cleaning or following curvy lines, can be dealt with using nonlinear vector fields. This article introduces a novel approach called the rotational obstacle avoidance method (ROAM) fo ...

Piscataway2024

A Theory of Finite-Width Neural Networks: Generalization, Scaling Laws, and the Loss Landscape

Berfin Simsek

Deep learning has achieved remarkable success in various challenging tasks such as generating images from natural language or engaging in lengthy conversations with humans.The success in practice stems from the ability to successfully train massive neural ...

EPFL2023

Language Model Decoding as Likelihood–Utility Alignment

Boi Faltings, Robert West, Maxime Jean Julien Peyrard, Martin Josifoski, Valentin Hartmann, Debjit Paul, Jiheng Wei, Frano Rajic

A critical component of a successful language generation pipeline is the decoding algorithm. However, the general principles that should guide the choice of a decoding algorithm re- main unclear. Previous works only compare decoding algorithms in narrow sc ...

2023

Model-based impurity emission front control using deuterium fueling and nitrogen seeding in TCV

Basil Duval, Christian Gabriel Theiler, Cristian Galperti, Artur Perek

This paper presents the first result using nitrogen-seeded exhaust feedback control of the NII impurity emission front in TCV. The NII emission front position is consistently located below its commonly used CIII counterpart, indicating the NII emission fro ...

IOP Publishing Ltd2023

Divertor detachment and reattachment with mixed impurity seeding on ASDEX Upgrade

Using newly developed spectroscopic models to measure the divertor concentration of Ne and Ar, it is shown that the experimental detachment threshold on ASDEX Upgrade with Ar-only and mixtures of Ar+N or Ne+N scales as expected in comparison with an analyt ...

IOP Publishing Ltd2023

Unraveling looping efficiency of stochastic Cosserat polymers

Raushan Singh, Giulio Corazza

Understanding looping probabilities, including the particular case of ring closure or cyclization, of fluctuating polymers (e.g., DNA) is important in many applications in molecular biology and chemistry. In a continuum limit the configuration of a polymer ...

AMER PHYSICAL SOC2022

Development of a new method to determine the axial void velocity profile in BWRs from measurements of the in-core neutron noise

Mathieu Hursin

Determination of the local void fraction in BWRs from in-core neutron noise measurements requires the knowledge of the axial velocity of the void. The purpose of this paper is to revisit the problem of determining the axial void velocity profile from the t ...

PERGAMON-ELSEVIER SCIENCE LTD2021

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Wulfram Gerstner, Clément Hongler, Johanni Michael Brea, Francesco Spadaro, Berfin Simsek, Arthur Jacot

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with

L

layers of minimal widths

r_1^*, \ldots, r_{L-1}^*

reaches a zero-loss minimum at $ r_1^*! \c ...

2021

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.