ETH-FDS seminar series

More information about ETH Foundations of Data Science can be found here

×

Modal title

Modal content

Please subscribe here if you would you like to be notified about these events via e-mail. Moreover you can also subscribe to the iCal/ics Calender.

Autumn Semester 2023

Date / Time Speaker Title Location
22 September 2023
15:15-16:15
Zijian Guo
Rutgers University, USA
Details

ETH-FDS seminar

Title Joint talk: Robust Causal Inference with Possibly Invalid Instruments: Post-selection Problems and A Solution Using Searching and Sampling
Speaker, Affiliation Zijian Guo, Rutgers University, USA
Date, Time 22 September 2023, 15:15-16:15
Location HG G 19.1
Abstract Instrumental variable methods are among the most commonly used causal inference approaches to deal with unmeasured confounders in observational studies. The presence of invalid instruments is the primary concern for practical applications, and a fast-growing area of research is inference for the causal effect with possibly invalid instruments. This paper illustrates that the existing confidence intervals may undercover when the valid and invalid instruments are hard to separate in a data-dependent way. To address this, we construct uniformly valid confidence intervals that are robust to the mistakes in separating valid and invalid instruments. We propose to search for a range of treatment effect values that lead to sufficiently many valid instruments. We further devise a novel sampling method, which, together with searching, leads to a more precise confidence interval. Our proposed searching and sampling confidence intervals are uniformly valid and achieve the parametric length under the finite-sample majority and plurality rules. We apply our proposal to examine the effect of education on earnings. The proposed method is implemented in the R package RobustIV available from CRAN.
Joint talk: Robust Causal Inference with Possibly Invalid Instruments: Post-selection Problems and A Solution Using Searching and Sampling read_more
HG G 19.1
2 November 2023
16:15-17:15
Quentin Berthet
Google DeepMind
Details

ETH-FDS seminar

Title Joint talk DACO-FDS: Perturbed Optimizers for Machine Learning
Speaker, Affiliation Quentin Berthet , Google DeepMind
Date, Time 2 November 2023, 16:15-17:15
Location HG G 19.1
Abstract Machine learning pipelines often rely on optimizers procedures to make discrete decisions (e.g., sorting, picking closest neighbors, or shortest paths). Although these discrete decisions are easily computed in a forward manner, they break the back-propagation of computational graphs. In order to expand the scope of learning problems that can be solved in an end-to-end fashion, we propose a systematic method to transform optimizers into operations that are differentiable and never locally constant. Our approach relies on stochastically perturbed optimizers, and can be used readily within existing solvers. Their derivatives can be evaluated efficiently, and smoothness tuned via the chosen noise amplitude. We also show how this framework can be connected to a family of losses developed in structured prediction, and give theoretical guarantees for their use in learning tasks. We demonstrate experimentally the performance of our approach on various tasks, including recent applications on protein sequences.
Joint talk DACO-FDS: Perturbed Optimizers for Machine Learningread_more
HG G 19.1
16 November 2023
16:15-17:15
Jakob Zech
Universität Heidelberg
Details

ETH-FDS seminar

Title Nonparametric Distribution Learning via Neural ODEs
Speaker, Affiliation Jakob Zech, Universität Heidelberg
Date, Time 16 November 2023, 16:15-17:15
Location HG G 19.1
Abstract In this talk, we explore approximation properties and statistical aspects of Neural Ordinary Differential Equations (Neural ODEs). Neural ODEs are a recently established technique in computational statistics and machine learning, that can be used to characterize complex distributions. Specifically, given a fixed set of independent and identically distributed samples from a target distribution, the goal is either to estimate the target density or to generate new samples. We first investigate the regularity properties of the velocity fields used to push forward a reference distribution to the target. This analysis allows us to deduce approximation rates achievable through neural network representations. We then derive a concentration inequality for the maximum likelihood estimator of general ODE-parametrized transport maps. By merging these findings, we are able to determine convergence rates in terms of both the network size and the number of required samples from the target distribution. Our discussion will particularly focus on target distributions within the class of positive $C^k$ densities on the $d$-dimensional unit cube $[0,1]^d$.
Nonparametric Distribution Learning via Neural ODEsread_more
HG G 19.1
JavaScript has been disabled in your browser