5 papers
Statistical Guarantees for Approximate Stationary Points of Shallow Neural Networks
Mahsa Taheri, Fang Xie, Johannes Lederer
Since statistical guarantees for neural networks are usually restricted to global optima of intricate objective functions, it is unclear whether these theories explain the performa…
Non-asymptotic error bounds for probability flow ODEs under weak log-concavity
Gitte Kremling, Francesco Iafrate, Mahsa Taheri +1
Score-based generative modeling, implemented through probability flow ODEs, has shown impressive results in numerous practical settings. However, most convergence guarantees rely o…
Regularization can make diffusion models more efficient
Mahsa Taheri, Johannes Lederer
Diffusion models are one of the key architectures of generative AI. Their main drawback, however, is the computational costs. This study indicates that the concept of sparsity, wel…
How many samples are needed to train a deep neural network?
Pegah Golestaneh, Mahsa Taheri, Johannes Lederer
Neural networks have become standard tools in many areas, yet many important statistical questions remain open. This paper studies the question of how much data are needed to train…
Adaptive tail index estimation: minimal assumptions and non-asymptotic guarantees
Johannes Lederer, Anne Sabourin, Mahsa Taheri
A notoriously difficult challenge in extreme value theory is the choice of the number , where is the total sample size, of extreme data points to consider for inference…