First and Zeroth-Order Implementations of the Regularized Newton Method with Lazy Approximated Hessians

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.

Context. Imaging in radio interferometry requires solving an ill-posed noisy inverse problem, for which the most adopted algorithm is the original CLEAN algorithm and its variants. Alternative explicit optimization methods have gained increasing attention, ...

Integer linear programming (ILP) is an elegant approach to solve linear optimization problems, naturally described using integer decision variables. Within the context of physics-inspired machine learning (ML) applied to chemistry, we demonstrate the relev ...

Adversarial examples crafted in black-box scenarios are affected by unrealistic colors or spatial artifacts. To prevent these shortcomings, we propose a novel strategy that generates adversarial images with low detectability and high transferability. The p ...

For robots to operate in unstructured environments, they are required to interact with objects through contact. Those contacts may be used to push objects to the side, deform objects, or manipulate objects in-hand. This thesis addresses the problem of cont ...

Quantum metrology, a cornerstone of quantum technologies, exploits entanglement and superposition to achieve higher precision than classical protocols in parameter-estimation tasks. When combined with critical phenomena such as phase transitions, the diver ...

We consider a network of agents that must solve an online optimization problem from continual observation of streaming data. To this end, the agents implement a distributed cooperative strategy where each agent is allowed to perform local exchange of infor ...

Given the prompt “Rome is in”, can we steer a language model to flip its prediction of an incorrect token “France” to a correct token “Italy” by only multiplying a few relevant activation vectors with scalars? We argue that successfully intervening on a mo ...

We propose a novel framework of generalised Petrov-Galerkin Dynamical Low Rank Approximations (DLR) in the context of random PDEs. It builds on the standard Dynamical Low Rank Approximations in their Dynamically Orthogonal formulation. It allows to seamles ...

We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this an ...

Kalman and H-infinity filters, the most popular paradigms for linear state estimation, are designed for very specific specific noise and disturbance patterns, which may not appear in practice. State observers based on the minimization of regret measures ar ...

This paper studies the problem of online performance optimization of constrained closed-loop control systems, where both the objective and the constraints are unknown black-box functions affected by exogenous time-varying contextual disturbances. A primal- ...

One of the main goal of Artificial Intelligence is to develop models capable of providing valuable predictions in real-world environments. In particular, Machine Learning (ML) seeks to design such models by learning from examples coming from this same envi ...

Microbubbles excited by acoustic fields inside water oscillate, and generate acoustic radiation forces and drag-induced acoustic streaming. These forces can be harnessed in various biomedical applications such as targeted drug delivery and on-chip biomanip ...

We develop a novel 2D functional learning framework that employs a sparsity-promoting regularization based on second-order derivatives. Motivated by the nature of the regularizer, we restrict the search space to the span of piecewise-linear box splines shi ...

In superstructure optimization of processes and energy systems, the design space is defined as the combination of unit considerations, process conditions and model parameters that might be subjected to uncertainty. Most of the time, decision makers are not ...

The parallel Schwarz method (PSM) is an overlapping domain decomposition (DD) method to solve partial differential equations (PDEs). Similarly to classical nonoverlapping DD methods, the PSM admits a substructured formulation, that is, it can be formulated ...

This paper presents a new All-In-One (AIO) implementation of an existing formulation to design adaptive structures through Total Energy Optimization (TEO). The method implemented in previous work is a nested optimization process, here named TEO-Nested. Num ...

Clustering is a classic topic in optimization with k-means being one of the most fundamental such problems. In the absence of any restrictions on the input, the best-known algorithm for k-means in Euclidean space with a provable guarantee is a simple local ...

Block Krylov subspace methods (KSMs) comprise building blocks in many state-of-the-art solvers for large-scale matrix equations as they arise, for example, from the discretization of partial differential equations. While extended and rational block Krylov ...

Decentralized optimization is a powerful paradigm that finds applications in engineering and learning design. This work studies decentralized composite optimization problems with non-smooth regularization terms. Most existing gradient-based proximal decent ...

First and Zeroth-Order Implementations of the Regularized Newton Method with Lazy Approximated Hessians

Chat with Graph Search

PolyCLEAN: Atomic optimization for super-resolution imaging and uncertainty estimation in radio interferometry

Integer Linear Programming for Unsupervised Training Set Selection in Molecular Machine Learning

GLoFool: Global Enhancements and Local Perturbations to Craft Adversarial Images

A Stochastic Approach to Contact-rich Manipulation

Criticality-Enhanced Quantum Sensing with a Parametric Superconducting Resonator

Distributed Adaptive Learning Under Communication Constraints

Activation Scaling for Steering and Interpreting Language Models

Petrov-Galerkin Dynamical Low Rank Approximation: SUPG stabilisation of advection-dominated problems

End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

Minimal regret state estimation of time-varying systems

Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraints

Predicting in Uncertain Environments: Methods for Robust Machine Learning

Dynamics of entrapped microbubbles with multiple openings

Learning of Continuous and Piecewise-Linear Functions With Hessian Total-Variation Regularization

Active learning for multi-objective optimization of processes and energy systems

Spectral Coarse Spaces for the Substructured Parallel Schwarz Method

Minimum energy adaptive structures – All-In-One problem formulation

Better Guarantees for k-Means and Euclidean k-Median by Primal-Dual Algorithms

Compress-and-restart block Krylov subspace methods for Sylvester matrix equations

A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization