Parsimonious Online Learning with Kernels and Random Features with Applications to Stochastic Optimal Control

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.

The barren plateau phenomenon, characterized by loss gradients that vanish exponentially with system size, poses a challenge to scaling variational quantum algorithms. Here we explore the potential of warm starts, whereby one initializes closer to a soluti ...

Symbolic Regression holds great potential for uncovering underlying mathematical and physical relationships from observed data. However, the vast combinatorial space of possible expressions poses significant challenges for previous online search methods an ...

High resolution multi-physics core solvers predict safety parameters on a local scale with high accuracy while simulating local heterogeneities and their consequences. To achieve this, large computational resources are needed which renders the extensive us ...

As modern machine learning continues to achieve unprecedented benchmarks, the resource demands to train these advanced models grow drastically. This has led to a paradigm shift towards distributed training. However, the presence of adversariesâ whether ma ...

Author summaryForecasting the short time evolution of the COVID-19 daily incidence is a key issue in the epidemic decision making policy. We propose a machine learning method which forecasts the future values of the daily incidence trend based on the evolu ...

Reducing the computational time required by high-fidelity, full-order models (FOMs) for the solution of problems in cardiac mechanics is crucial to allow the translation of patient-specific simulations into clinical practice. Indeed, while FOMs, such as th ...

Modern machine learning (ML) models are capable of impressive performances. However, their prowess is not due only to the improvements in their architecture and training algorithms but also to a drastic increase in computational power used to train them.|S ...

The advent of comprehensive synaptic wiring diagrams of large neural circuits has created the field of connectomics and given rise to a number of open research questions. One such question is whether it is possible to reconstruct the information stored in ...

We study the problem of drift estimation for two-scale continuous time series. We set ourselves in the framework of overdamped Langevin equations, for which a single-scale surrogate homogenized equation exists. In this setting, estimating the drift coeffic ...

Deep neural networks can be fragile and sensitive to small input perturbations that might cause a significant change in the output. In this letter, we employ contraction theory to improve the robustness of neural ODEs (NODEs). A dynamical system is contrac ...

Closed-loop neural interfaces with on-chip machine learning can detect and suppress disease symptoms in neurological disorders or restore lost functions in paralyzed patients. While high-density neural recording can provide rich neural activity information ...

3D reconstruction of pulmonary segments plays an important role in surgical treatment planning of lung cancer, which facilitates preservation of pulmonary function and helps ensure low recurrence rates. However, automatic reconstruction of pulmonary segmen ...

We study the problem of performance optimization of closed-loop control systems with unmodeled dynamics. Bayesian optimization (BO) has been demonstrated effective for improving closed-loop performance by automatically tuning controller gains or reference ...

We consider the estimation of a nxm matrix uv(T) observed through an additive Gaussian noise channel, a problem that frequently arises in statistics and machine learning. We investigate a scenario involving mismatched Bayesian inference in which the stat ...

Generalized empirical currents represent a vast class of thermodynamic observables of mesoscopic systems. Their fluctuations satisfy the thermodynamic uncertainty relations (TURs), as they can be bounded by the average entropy production. Here, we derive a ...

With the current exponential growth of video-based social networks, video retrieval using natural language is receiving ever-increasing attention. Most existing approaches tackle this task by extracting individual frame-level spatial features to represent ...

Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning rich feature extractors from large datasets. However, most deep learning classification methods are ...

Parsimonious Online Learning with Kernels and Random Features with Applications to Stochastic Optimal Control

Chattez avec Graph Search

Variational Quantum Simulation: A Case Study for Understanding Warm Starts

Interactive symbolic regression with co-design mechanism through offline reinforcement learning

High-Resolution Predictions of the Fuel and Cladding Temperatures for the 3D PWR Core with Artificial Neural Networks trained on CTF

Distributed Optimization with Byzantine Robustness Guarantees

Learning from the past: A short term forecast method for the COVID-19 incidence curve

Efficient approximation of cardiac mechanics through reduced-order modeling with deep learning-based operator approximation

Byzantine-Resilient Learning Beyond Gradients: Distributing Evolutionary Search

Bayesian reconstruction of memories stored in neural networks from their connectivity

Drift Estimation of Multiscale Diffusions Based on Filtered Data

Robust Classification Using Contractive Hamiltonian Neural ODEs

NeuralTree: A 256-Channel 0.227-mu J/Class Versatile Neural Activity Classification and Closed-Loop Neuromodulation SoC

What Makes for Automatic Reconstruction of Pulmonary Segments

VABO: Violation-Aware Bayesian Optimization for Closed-Loop Control Performance Optimization with Unmodeled Constraints

Mismatched Estimation of Non-Symmetric Rank-One Matrices Under Gaussian Noise

Hyperaccurate bounds in discrete-state Markovian systems

Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval

Fidelity Estimation Improves Noisy-Image Classification with Pretrained Networks