Neural Redshift: Random Networks are not Random Functions

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.

Demographic fairness or equity is a crucial aspect of machine learning models, particularly in critical domains such as healthcare, where errors can have severe consequences. A fair model avoids making distinctions between groups with different sensitive o ...

A payment channel network is a blockchain-based overlay mechanism that allows parties to transact more efficiently than directly using the blockchain. These networks are composed of payment channels that carry transactions between pairs of users. Due to it ...

The unifying theme of this thesis are decision trees. Given a boolean function

f

and an input

x

, a decision tree computes the value

f(x)

by repeatedly querying bits of

x

. Our work is two-fold. On one hand, we investigate direct sums and other relat ...

We study the random binary symmetric perceptron problem, focusing on the behavior of rare high-margin solutions. While most solutions are isolated, we demonstrate that these rare solutions are part of clusters of extensive entropy, heuristically correspond ...

The increasing complexity of transformer models in artificial intelligence expands their computational costs, memory usage, and energy consumption. Hardware acceleration tackles the ensuing challenges by designing processors and accelerators tailored for t ...

Accurate human trajectory prediction is crucial for applications such as autonomous vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage the non-verbal social cues human subconsciously communicate when navigating ...

By 'social learning,' in this article we refer to mechanisms for opinion formation and decision making over graphs and the study of how agents' decisions evolve dynamically through interactions with neighbors and the environment. The study of social learni ...

The sum-of-squares (SOS) approximation method is a technique used in optimization problems to derive lower bounds on the optimal value of an objective function. By representing the objective function as a sum of squares in a feature space, the SOS method t ...

Deep neural networks trained on physical losses are emerging as promising surrogates for nonlinear numerical solvers. These tools can predict solutions to Maxwell's equations and compute gradients of output fields with respect to the material and geometric ...

Data redundancy has been one of the most important problems in data-intensive applications such as data mining and machine learning. Removing data redundancy brings many benefits in efficient data updating, effective data storage, and error-free query proc ...

Supplementary files containing datasets needed to reproduce the results of the manuscript "Generative machine learning produces kinetic models that accurately characterize intracellular metabolic states" by S. Choudhury et al. The code to use with these da ...

In this article, we study the problem of Byzantine fault-tolerance in a federated optimization setting, where there is a group of agents communicating with a centralized coordinator. We allow up to

f

Byzantine-faulty agents, which may not follow a prescr ...

A novel technique based on machine learning is introduced to reconstruct the decays of highly Lorentz boosted particles. Using an end-to-end deep learning strategy, the technique bypasses existing rule-based particle reconstruction methods typically used i ...

In this thesis, we propose and analyze novel numerical algorithms for solving three different high-dimensional problems involving tensors. The commonality of these problems is that the tensors can potentially be well approximated in low-rank formats. Ident ...

Neural Redshift: Random Networks are not Random Functions

Chat with Graph Search

Optimizing fairness and utility in healthcare machine learning models

Pricing for Routing and Flow-control in Payment Channel Networks

The Power of Decision Trees for Composition and Search Problems

On the atypical solutions of the symmetric binary perceptron

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

Social-Transmotion: Promptable Human Trajectory Prediction

Statistical mechanics of deep learning

Socially Intelligent Networks: A framework for decision making over graphs

Theory and applications of the sum-of-squares technique

Predicting nonlinear optical scattering with physics-driven neural networks

Validating functional redundancy with mixed generative adversarial networks

Supplementary datasets for the manuscript "Generative machine learning produces kinetic models that accurately characterize intracellular metabolic states" -Part 2

Byzantine Fault-Tolerance in Federated Local SGD Under 2f-Redundancy

Reconstruction of decays to merged photons using end-to-end deep learning with domain continuation in the CMS detector

Low-Rank Tensor Methods for High-Dimensional Problems