Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo

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.

In this work, we develop first-order (Hessian-free) and zeroth-order (derivative-free) implementations of the Cubically Regularized Newton Method for solving general non-convex optimization problems. For that, we employ finite difference approximations of ...

Fuel performance codes are essential for predicting fuel rod behavior in nuclear reactors. These codes comprise a complex system of models with empirical constants that require calibration against experimental data. To support this calibration, this study ...

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

We propose a novel approach to evaluating the ionic Seebeck coefficient in electrolytes from relatively short equilibrium molecular dynamics simulations, based on the Green-Kubo theory of linear response and Bayesian regression analysis. By exploiting the ...

Gels made of telechelic polymers connected by reversible cross-linkers are a versatile design platform for biocompatible viscoelastic materials. Their linear response to a step strain displays a fast, near-exponential relaxation when using low-valence cros ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

We consider the problem of defining and fitting models of autoregressive time series of probability distributions on a compact interval of Double-struck capital R. An order-1 autoregressive model in this context is to be understood as a Markov chain, where ...

Many applications, e.g. in content recommendation, sports, or recruitment, leverage the comparisons of alternatives to score those alternatives. The classical Bradley-Terry model and its variants have been widely used to do so. The historical model conside ...

Atomistic simulations performed with a family of model potential with tunable hardness have proven to be a great tool for advancing the understanding of wear processes at the asperity level. They have been instrumental in finding a critical length scale, w ...

Herein, machine learning (ML) models using multiple linear regression (MLR), support vector regression (SVR), random forest (RF) and artificial neural network (ANN) are developed and compared to predict the output features viz. specific capacitance (Csp), ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

A key challenge across many disciplines is to extract meaningful information from data which is often obscured by noise. These datasets are typically represented as large matrices. Given the current trend of ever-increasing data volumes, with datasets grow ...

Extracting maximal information from experimental data requires access to the likelihood function, which however is never directly available for complex experiments like those performed at high energy colliders. Theoretical predictions are obtained in this ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

Zoning reform is a crucial tool for cities to adapt to contemporary challenges. However, its implementation remains challenging. Property owners, with a vested interest in the value of their neighborhoods, are sensitive to local developments and the potent ...

Under resource constraints, LLMs are usually fine- tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new ...

Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo

Chat with Graph Search

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

Preliminary Sensitivity Analysis of Time-Dependent Code Outputs in Fuel Performance Models Using OFFBEAT for Future Calibration

Extensions of Peer Prediction Incentive Mechanisms

Seebeck Coefficient of Ionic Conductors from Bayesian Regression Analysis

Valence can control the nonexponential viscoelastic relaxation of multivalent reversible gels

Random matrix methods for high-dimensional machine learning models

Generalization of Scaled Deep ResNets in the Mean-Field Regime

On distributional autoregression and iterated transportation

Generalized Bradley-Terry Models for Score Estimation from Paired Comparisons

A story of two transitions: From adhesive to abrasive wear and from ductile to brittle regime

Machine learning models for prediction of electrochemical properties in supercapacitor electrodes using MXene and graphene nanoplatelets

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Spectral Estimators for High-Dimensional Matrix Inference

Boosting likelihood learning with event reweighting

Topics in statistical physics of high-dimensional machine learning

On the Generalization of Stochastic Gradient Descent with Momentum

Robust machine learning for neuroscientific inference

Understanding generalization and robustness in modern deep learning

Spatial Modeling for Building Design Evaluation: from Visual Landscape Quality Assessment to Devaluation Risk Estimation

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security