Momentum-Based Policy Gradient with Second-Order Information

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.

We develop a model-free approach to optimally control stochastic, Markovian systems subject to a reach-avoid constraint. Specifically, the state trajectory must remain within a safe set while reaching a target set within a finite time horizon. Due to the t ...

Machine learning and artificial intelligence methods have achieved remarkable success, matching and even surpassing human capabilities in various complex tasks. However, many demonstrations have generally neglected a critical part of the intelligence that ...

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

The application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers ...

We study the generalization of iterative noisy gradient schemes on smooth non-convex losses. Formally, we establish time-independent information theoretic generalization bounds for Stochastic Gradient Langevin Dynamics (SGLD) that do not diverge as the ite ...

Sharing data across institutions for genome-wide association studies (GWAS) would enhance the discovery of genetic variation linked to health and disease1,2. However, existing data-sharing regulations limit the scope of such collaborations3. Although crypt ...

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 ...

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 ...

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 ...

Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social in ...

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

Epilepsy, a major neurological disease, requires careful diagnosis and treatment. However, the detection of epileptic seizures remains a significant challenge. Current clinical practice relies on expert analysis of EEG signals, a process that is time-consu ...

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 ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

Human babies have a natural desire to interact with new toys and objects, through which they learn how the world around them works, e.g., that glass shatters when dropped, but a rubber ball does not. When their predictions are proven incorrect, such as whe ...

Buildings play a pivotal role in the ongoing worldwide energy transition, accounting for 30% of the global energy consumption. With traditional engineering solutions reaching their limits to tackle such large-scale problems, data-driven methods and Machine ...

Accurate forecasting of photovoltaic (PV) power production is crucial for the integration of more renewable energy sources into the power grid. PV power production is highly intermittent, due to the stochastic cloud behaviour and cloud dynamics. Previous w ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Momentum-Based Policy Gradient with Second-Order Information

Chat with Graph Search

A learning-based approach to stochastic optimal control under reach-avoid constraint

Sequential Reasoning with Socially Caused Beliefs

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Scalable kernel logistic regression with Nyström approximation: Theoretical analysis and application to discrete choice modelling

Generalization of Noisy SGD in Unbounded Non-convex Settings

Secure and federated genome-wide association studies for biobank-scale datasets

Understanding generalization and robustness in modern deep learning

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Topics in statistical physics of high-dimensional machine learning

Predicting the long-term collective behaviour of fish pairs with deep learning

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Partial discharge localization in power transformer tanks using machine learning methods

Resource-Efficient Continual Learning for Personalized Online Seizure Detection

Spectral Estimators for High-Dimensional Matrix Inference

Incorporating Projective Geometry into Deep Learning

Seeking the new, learning from the unexpected: Computational models of surprise and novelty in the brain

Fusing Pre-existing Knowledge and Machine Learning for Enhanced Building Thermal Modeling and Control

Network time series forecasting in photovoltaics power production

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks