Universal Gradient Methods for Stochastic Convex Optimization

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 application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers ...

The evolution of airborne mapping witnesses the introduction of hybrid lidar-camera systems to enhance data collection, i.e. to obtain simultaneously high-density point-cloud and texture. Yet, the common adjustment of both optical data streams is a nontriv ...

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 ...

Data-driven techniques are increasingly used to replace electronic-structure calculations of matter. In this context, a relevant question is whether machine learning (ML) should be applied directly to predict the desired properties or combined explicitly w ...

Deep learning has achieved remarkable success in various challenging tasks such as generating images from natural language or engaging in lengthy conversations with humans. The success in practice stems from the ability to successfully train massive neural ...

Semi-discrete optimal transport problems, which evaluate the Wasserstein distance between a discrete and a generic (possibly non-discrete) probability measure, are believed to be computationally hard. Even though such problems are ubiquitous in statistics, ...

In this thesis we design online combinatorial optimization algorithms for beyond worst-case analysis settings. In the first part, we discuss the online matching problem and prove that, in the edge arrival model, no online algorithm can achieve a competiti ...

In the last decade, deep neural networks have achieved tremendous success in many fields of machine learning. However, they are shown vulnerable against adversarial attacks: well-designed, yet imperceptible, perturbations can make the state-of-the-art deep ...

The objective of meta-learning is to exploit knowledge obtained from observed tasks to improve adaptation to unseen tasks. Meta-learners are able to generalize better when they are trained with a larger number of observed tasks and with a larger amount of ...

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware neural architecture ...

Integrating functions on discrete domains into neural networks is key to developing their capability to reason about discrete objects. But, discrete domains are (I) not naturally amenable to gradient-based optimization, and (II) incompatible with deep lear ...

In this paper, we study an emerging class of neural networks, the Morphological Neural networks, from some modern perspectives. Our approach utilizes ideas from tropical geometry and mathematical morphology. First, we state the training of a binary morphol ...

We characterize the solution of a broad class of convex optimization problems that address the reconstruction of a function from a finite number of linear measurements. The underlying hypothesis is that the solution is decomposable as a finite sum of compo ...

In distributed optimization, parameter updates from the gradient computing node devices have to be aggregated in every iteration on the orchestrating server. When these updates are sent over an arbitrary commodity network, bandwidth and latency can be limi ...

The emergence of Big Data has enabled new research perspectives in the discrete choice community. While the techniques to estimate Machine Learning models on a massive amount of data are well established, these have not yet been fully explored for the esti ...

Nowadays, Deep Convolutional Neural Networks (DCNNs) play a significant role in many application domains, such as, computer vision, medical imaging, and image processing. Nonetheless, designing a DCNN, able to defeat the state of the art, is a manual, chal ...

Over the past few years, there have been fundamental breakthroughs in core problems in machine learning, largely driven by advances in deep neural networks. The amount of annotated data drastically increased and supervised deep discriminative models exceed ...

This study evaluates the potential of supervised and transfer learning techniques to assist energy system optimization. A surrogate model is developed with the support of a supervised learning technique (by using artificial neural network) in order to bypa ...

This paper considers optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that enforce the objectives across the network to lie in a low-dimensiona ...

Graph spectral analysis can yield meaningful embeddings of graphs by providing insight into distributed features not directly accessible in nodal domain. Recent efforts in graph signal processing have proposed new decompositions-for example, based on wavel ...

Universal Gradient Methods for Stochastic Convex Optimization

Chat with Graph Search

Scalable kernel logistic regression with Nyström approximation: Theoretical analysis and application to discrete choice modelling

On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation

Understanding generalization and robustness in modern deep learning

Electronic Excited States from Physically Constrained Machine Learning

A Theory of Finite-Width Neural Networks: Generalization, Scaling Laws, and the Loss Landscape

Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution

Beyond worst-case analysis, with or without predictions

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks

Dif-MAML: Decentralized Multi-Agent Meta-Learning

U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search

Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions

Advances In Morphological Neural Networks: Training, Pruning And Enforcing Shape Constraints

Convex optimization in sums of Banach spaces

LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads

Estimation of discrete choice models with hybrid stochastic adaptive batch size algorithms

Multi-Agent Reinforcement Learning for Hyperparameter Optimization of Deep Convolutional Neural Networks

Deep Generative Models and Applications

Machine learning methods to assist energy system optimization

Distributed Inference Over Networks Under Subspace Constraints

Guided graph spectral embedding: Application to the C. elegans connectome