When do Minimax-fair Learning and Empirical Risk Minimization Coincide?

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.

This work studies the learning process over social networks under partial and random information sharing. In traditional social learning models, agents exchange full belief information with each other while trying to infer the true state of nature. We stud ...

Activity-based models offer the potential for a far deeper understanding of daily mobility behaviour than trip-based models. Based on the fundamental assumption that travel demand is derived from the need to do activities, they are flexible tools that aim ...

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 ...

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 ...

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 ...

IceCube Collaboration has previously reported evidence for a neutrino signal from a Seyfert galaxy NGC 1068. This may suggest that all Seyfert galaxies emit neutrinos. To test this hypothesis, we identify the best candidate neutrino sources among nearby Se ...

The pursuit of software security and reliability hinges on the identification and elimination of software vulnerabilities, a challenge compounded by the vast and evolving complexity of modern systems. Fuzzing has emerged as an indispensable technique for b ...

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 ...

Parliament dynamics might seem erratic at times. Predicting future voting patterns could support policy design based on the simulation of voting scenarios. The availability of open data on legislative activities and machine learning tools might enable such ...

Professionals in the building design and operation fields typically look at standards and guidelines as a reliable source of information and guidance with regard to procedural, contractual, and legal scope and requirements that are relevant to accountabili ...

Imai et al.(IJGHS) have conducted a timely experiment on evaluating a decision support algorithm. However, we are concerned by their choice of estimands which, even if they appear plausible at first, rely on notions and assumptions for which we cannot ever ...

This thesis studies the origins and consequences of financial crises, and computational techniques to solve continuous-time economic models that explain such crises. The first chapter shows that financial recessions are typically characterised by a large ...

We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this an ...

The performance of modern object detectors drops when the test distribution differs from the training one. Most of the methods that address this focus on object appearance changes caused by, e.g., different illumination conditions, or gaps between syntheti ...

This work addresses the problem of sharing partial information within social learning strategies. In social learning, agents solve a distributed multiple hypothesis testing problem by performing two operations at each instant: first, agents incorporate inf ...

By replacing part of Portland cement with so-called supplementary cementitious materials (SCMs) it is possible to reduce the CO2 footprint of the cement industry. These SCMs are commonly limestone, calcined clay, slag and fly ash. While doing so the early ...

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 ...

A critical component of a successful language generation pipeline is the decoding algorithm. However, the general principles that should guide the choice of a decoding algorithm re- main unclear. Previous works only compare decoding algorithms in narrow sc ...

We investigate the response of the free liquid surface in a partially filled circular cylindrical container undergoing a planar elliptic and time-periodic orbit while maintaining fixed its orientation. For small forcing amplitudes and deep liquid layers, w ...

Novel usages of brain stimulation combined with artificially intelligent (AI) systems promise to address a large range of diseases. These new conjoined technologies, such as brain-computer interfaces (BCI), are increasingly used in experimental and clinica ...

When do Minimax-fair Learning and Empirical Risk Minimization Coincide?

Chat with Graph Search

Social Opinion Formation and Decision Making Under Communication Trends

OASIS: An integrated optimisation framework for activity scheduling

Robust machine learning for neuroscientific inference

On the Generalization of Stochastic Gradient Descent with Momentum

Random matrix methods for high-dimensional machine learning models

Neutrino Signal from a Population of Seyfert Galaxies

To Infinity, and Beyond (Coverage)

Understanding generalization and robustness in modern deep learning

Predicting party switching through machine learning and open data

Thermal Conditions in Indoor Environments: Exploring the Reasoning behind Standard-Based Recommendations

Discussion of ‘Experimental Evaluation of Algorithm-Assisted Human Decision-Making: Application to Pretrial Public Safety Assessment’, part 2

Essays in macro-finance and deep learning

End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

Learning Transformations To Reduce the Geometric Shift in Object Detection

Partial Information Sharing Over Social Learning Networks

Atomistic modeling of C-S-H: bulk and surface

Multi-agent Learning with Privacy Guarantees

Language Model Decoding as Likelihood–Utility Alignment

Swirling against the forcing: Evidence of stable counterdirected sloshing waves in orbital-shaken reservoirs

How I became myself after merging with a computer: Does human-machine symbiosis raise human rights issues?