Predicting in Uncertain Environments: Methods for Robust Machine Learning

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.

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

Scientific Machine Learning (SciML) is a recently emerged research field which combines physics-based and data-driven models for the numerical approximation of differential problems. Physics-based models rely on the physical understanding of the problem at ...

We develop new tools to study landscapes in nonconvex optimization. Given one optimization problem, we pair it with another by smoothly parametrizing the domain. This is either for practical purposes (e.g., to use smooth optimization algorithms with good g ...

Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and dep ...

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 ...

BackgroundBronchiolitis Obliterans Syndrome (BOS), a fibrotic airway disease that may develop after lung transplantation, conventionally relies on pulmonary function tests (PFTs) for diagnosis due to limitations of CT imaging. Deep neural networks (DNNs) h ...

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 ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Image steganalysis, detecting hidden data in digital images, is essential for enhancing digital security. Traditional steganalysis methods typically rely on large, pre-labeled image datasets, which are difficult and costly to compile. To address this, this ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

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 ...

Given a ground-level query image and a geo-referenced aerial image that covers the query’s local surroundings, fine-grained cross-view localization aims to estimate the location of the ground camera inside the aerial image. Recent works have focused on dev ...

Orthogonal group synchronization is the problem of estimating n elements Z(1),& mldr;,Z(n) from the rxr orthogonal group given some relative measurements R-ij approximate to Z(i)Z(j)(-1). The least-squares formulation is nonconvex. To avoid its local minim ...

The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of O(ϵ-2) to achieve an ϵ-stationary solut ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

Magnons are the quanta of spin waves and transport angular momenta through magnetically ordered materials. They can be used to distribute and control on-chip GHz signals without charge flow, thereby avoiding Joule heating. Beyond multiplexed signal process ...

Modern optimization is tasked with handling applications of increasingly large scale, chiefly due to the massive amounts of widely available data and the ever-growing reach of Machine Learning. Consequently, this area of research is under steady pressure t ...

To retrieve Surface Solar Radiation (SSR) from satellite images, a baseline reflectance of the observed ground in clear-sky conditions, also called background reflectance, is necessary to distinguish atmospheric absorption and scattering effects from surfa ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

Synthesizability in generative molecular design remains a pressing challenge. Existing methods to assess synthesizability include heuristics-based metrics or retrosynthesis models which predict a synthetic pathway. By contrast, an explicit approach anchors ...

Predicting in Uncertain Environments: Methods for Robust Machine Learning

Chat with Graph Search

Safe Deep Neural Networks

Combining physics-based and data-driven models: advancing the frontiers of research with scientific machine learning

The effect of smooth parametrizations on nonconvex optimization landscapes

MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT

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

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Image steganalysis using active learning and hyperparameter optimization

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Random matrix methods for high-dimensional machine learning models

Adapting Fine-Grained Cross-View Localization to Areas Without Fine Ground Truth

BENIGN LANDSCAPES OF LOW-DIMENSIONAL RELAXATIONS FOR ORTHOGONAL SYNCHRONIZATION ON GENERAL GRAPHS

Diffusion Stochastic Optimization for Min-Max Problems

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Perspective on nonvolatile magnon-signal storage and in-memory computation for low-power consuming magnonics

Scalable constrained optimization

Retrieval of Surface Solar Radiation through Implicit Albedo Recovery from Temporal Context

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Directly optimizing for synthesizability in generative molecular design using retrosynthesis models