Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron

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.

Artificial Intelligence has revolutionized numerous fields, driving advancements in healthcare, finance, and autonomous systems. At the core of this revolution lies Deep Learning---algorithms that learn representations from data through computational layer ...

Deep reinforcement learning (DRL) is a powerful method for local motion planning in automated driving. However, training of DRL agents is difficult and subject to instability. We propose Regularized Adversarial Fine-Tuning (RAFT), an adversarial DRL traini ...

The electronic density of states (DOS) provides information regarding the distribution of electronic energy levels in a material, and can be used to approximate its optical and electronic properties and therefore guide computational materials design. Given ...

Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (a.k.a. FL clients) to train the same local model. This design is not well-suited for scenarios involving data and/or system ...

Automatic speech recognition (ASR) and spoken language understanding (SLU) is the core component of current voice-powered AI assistants such as Siri and Alexa. It involves speech transcription with ASR and its comprehension with natural language understand ...

A multi-agent system consists of a collection of decision-making or learning agents subjected to streaming observations from some real-world phenomenon. The goal of the system is to solve some global learning or optimization problem in a distributed or dec ...

Meta-Learning aims to speed up the learning process on new tasks by acquiring useful inductive biases from datasets of related learning tasks. While, in practice, the number of related tasks available is often small, most of the existing approaches assume ...

Perovskite solar cells are among the most dominant emerging PV technologies which have shown unparallel improvement in power conversion efficiency in just over a decade. Long charge carrier diffusion lengths and lifetimes, high absorption coefficients, ban ...

In several machine learning settings, the data of interest are well described by graphs. Examples include data pertaining to transportation networks or social networks. Further, biological data, such as proteins or molecules, lend themselves well to graph- ...

Many pathologies cause impairments in the speech production mechanism resulting in reduced speech intelligibility and communicative ability. To assist the clinical diagnosis, treatment and management of speech disorders, automatic pathological speech asses ...

The phenomenon of online dating via web and mobile phone applications involves several actors: graphical interfaces, developers, algorithmic systems for user matching, and users. These actors have been studied in parallel by the social sciences and by comp ...

Could a gradient aggregation rule (GAR) for distributed machine learning be both robust and fast? This paper answers by the affirmative through Multi-Bulyan. Given n workers, f of which are arbitrary malicious (Byzantine) and m = n − f are not, we prove th ...

The standard practice in Generative Adversarial Networks (GANs) discards the discriminator during sampling. However, this sampling method loses valuable information learned by the discriminator regarding the data distribution. In this work, we propose a co ...

Machine-learning in quantum chemistry is currently booming, with reported applications spanning all molecular properties from simple atomization energies to complex mathematical objects such as the many-body wavefunction. Due to its central role in density ...

Metal-organic framework (MOFs) and related nanoporous materials have emerged as promising candidates for a variety of applications, such as gas separation and storage, catalysis, sensing, etc. Their building block structure allows us to generate a huge num ...

The nonparametric learning of positive-valued functions appears widely in machine learning, especially in the context of estimating intensity functions of point processes. Yet, existing approaches either require computing expensive projections or semidefin ...

The very shallow geothermal potential (vSGP) is increasingly recognized as a viable resource for providing clean thermal energy in urban and rural areas. This is primarily due to its reliability, low-cost installation, easy maintenance, and little constrai ...

In our recent work, the sampling and reconstruction of non-decaying signals, modeled as members of weighted-L-p spaces, were shown to be stable with an appropriate choice of the generating kernel for the shift-invariant reconstruction space. In this paper, ...

Deep neural network (DNN) inference tasks are computationally expensive. Digital DNN accelerators offer better density and energy efficiency than general-purpose processors but still not sufficient to be deployable on resource-constrained settings.Analog c ...

We introduce a new method to price American options based on Chebyshev interpolation. In each step of a dynamic programming time-stepping we approximate the value function with Chebyshev polynomials. The key advantage of this approach is that it allows us ...

Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron

Chat with Graph Search

How data structures affect generalization in Kernel Methods and Deep Learning

RAFT: Regularized Adversarial Fine-Tuning to Enhance Deep Reinforcement Learning for Self-Parking

Adaptive energy reference for machine-learning models of the electronic density of states

FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning

Low-Resource Speech Recognition and Understanding for Challenging Applications

Multi-agent Learning with Privacy Guarantees

Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice

Critical analysis of decision variables for high-throughput experimentation (HTE) with perovskite solar cells

Graph Representation Learning with Optimal Transport: Analysis and Applications

Automatic pathological speech assessment

Online Dating Quantification Practices: A Human-Machine Learning Process

Fast and Robust Distributed Learning in High Dimension

Collaborative Sampling in Generative Adversarial Networks

Learning (from) the Electron Density: Transferability, Conformational and Chemical Diversity

Advancing computational and data-driven methods for the design and discovery of nanoporous materials

Learning Positive Functions with Pseudo Mirror Descent

A machine learning approach for mapping the very shallow theoretical geothermal potential

Approximation of Non-decaying Signals from Shift-Invariant Subspaces

Analog Neural Networks with Deep-submicron Nonlinear Synapses

A New Approach For American Option Pricing: The Dynamic Chebyshev Method