Stable Nonconvex-Nonconcave Training via Linear Interpolation

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.

In this paper, we present a new parameterization and optimization procedure for minimizing the weight of ribbed plates. The primary goal is to reduce embodied CO2 in concrete floors as part of the effort to diminish the carbon footprint of the construction ...

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

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 ...

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

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 ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

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 ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

We study quantifiers and interpolation properties in ortho- logic, a non-distributive weakening of classical logic that is sound for formula validity with respect to classical logic, yet has a quadratic-time decision procedure. We present a sequent-based p ...

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 ...

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 ...

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 ...

We report the detailed background for the discovery and development of the synthesis of homopropargylic azides by the azidoalkynylation of alkenes. Initially, a strategy involving SOMOphilic alkynes was adopted, but only resulted in a 29% yield of the desi ...

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Electrical stimulation of the visual nervous system could improve the quality of life of patients affected by acquired blindness by restoring some visual sensations, but requires careful optimization of stimulation parameters to produce useful perceptions. ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

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 ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Chat with Graph Search

Mesh-based topology, shape and sizing optimization of ribbed plates

Residual-based attention in physics-informed neural networks

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Enabling Uncertainty Estimation in Iterative Neural Networks

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

Topics in statistical physics of high-dimensional machine learning

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Interpolation and Quantifiers in Ortholattices

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

Scalable constrained optimization

Random matrix methods for high-dimensional machine learning models

SOMOphilic alkyne vs radical-polar crossover approaches: The full story of the azido-alkynylation of alkenes

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Decoding electroencephalographic responses to visual stimuli compatible with electrical stimulation

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Safe Deep Neural Networks

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks