Research

Research is a major part in the Machine Learning field. With multiple publications each year, we are standing within the best.

Warning

Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.

2024

Energy-Efficient Frequency Selection Method for Bio-Signal Acquisition in AI/ML Wearables

H. Taji; J. A. Miranda Calero; M. Peon Quiros; D. Atienza Alonso

2024-07-04. ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED ’24), Newport Beach, CA, USA, August 5–7, 2024. DOI : 10.1145/3665314.3670815.

Research

2024

Energy-Efficient Frequency Selection Method for Bio-Signal Acquisition in AI/ML Wearables

Learning to Remove Cuts in Integer Linear Programming

Improving SAM Requires Rethinking its Optimization Formulation

Robust NAS under adversarial training: benchmark, theory, and beyond

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Efficient Continual Finite-Sum Minimization

Revisiting Character-level Adversarial Attacks for Language Models

Efficient local linearity regularization to overcome catastrophic overfitting

Imitation Learning in Discounted Linear MDPs without exploration assumptions

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

2023

Review on Uric Acid Recognition by MOFs with a Future in Machine Learning

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

A Multimodal Dataset for Automatic Edge-AI Cough Detection

Trusting the Explainers: Teacher Validation of Explainable Artificial Intelligence for Course Design

Efficient Online Clustering with Moving Costs

Maximum Independent Set: Self-Training through Dynamic Programming

Alternation makes the adversary weaker in two-player games

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling

On the Convergence of Encoder-only Shallow Transformers

Towards more Practical Threat Models in Artificial Intelligence Security

Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.

Benign Overfitting in Deep Neural Networks under Lazy Training

What can online reinforcement learning with function approximation benefitfrom general coverage conditions

Out of their minds? Externalist challenges for using AI in forensic psychiatry

Advancing Computational Chemistry with Stochastic and Artificial Intelligence Approaches

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

Federated Learning under Covariate Shifts with Generalization Guarantees

A Multimodal Dataset for Automatic Edge-AI Cough Detection

Regularization of polynomial networks for image recognition

Domain Imaging and Switching Dynamics in BaTiO3-Based Photonic Integrated Devices

Analytical Engines With Context-Rich Processing: Towards Efficient Next-Generation Analytics

Distributed Extra-Gradient With Optimal Complexity And Communication Guarantees

Finding Actual Descent Directions For Adversarial Training

DiGress: Discrete Denoising diffusion for graph generation

Solving stochastic weak Minty variational inequalities without increasing batch size

Revisiting adversarial training for the worst-performing class

Towards Robust Monitoring of the Laser Powder Bed Fusion Process based on Acoustic Emission combined with Machine Learning Solutions

2022

SELFIES and the future of molecular string representations

BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration

UNDERGRAD: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees

No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

Extra Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods

Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Generalization Properties of NAS under Activation and Skip Connection Search

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

On the Double Descent of Random Features Models Trained with SGD

Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration

Proximal Point Imitation Learning

Identifiability and Generalizability from Multiple Experts in Inverse Reinforcement Learning

Sound and Complete Verification of Polynomial Networks

Karl Jaspers and artificial neural nets: on the relation of explaining and understanding artificial intelligence in medicine

Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize

Controlling the Complexity and Lipschitz Constant improves Polynomial Nets

The spectral bias of polynomial neural networks

Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems

2021

Local plasticity rules can learn deep representations using self-supervised contrastive predictions

Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)

What can linearized neural networks actually say about generalization?

Machine Learning Uncovers Aerosol Size Information From Chemistry and Meteorology to Quantify Potential Cloud-Forming Particles

GARFIELD: System Support for Byzantine Machine Learning (Regular Paper)

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Fitting summary statistics of neural data with a differentiable spiking network simulator

Mixed Nash Equilibria in the Adversarial Examples Game

A Plug-and-Play Deep Image Prior

Sifting through the Noise: Universal First-Order Methods for Stochastic Variational Inequalities

Convergence of adaptive algorithms for constrained weakly convex optimization

STORM+: Fully Adaptive SGD with Momentum for Nonconvex Optimization

A first-order primal-dual method with adaptivity to local smoothness

Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch

The Effect of the Intrinsic Dimension on the Generalization of Quadratic Classifiers