Our seminar | appliedAI — TransferLab

Our seminar

Roughly every Thursday afternoon. ML, RL, DL and statistics. We schedule talks on many domains and of varying difficulty levels, ranging from basic statistics to recent advances in RL. If you are interested in participating, drop us a line, we promise we won’t spam you.

Schedule

Data (e)valuation and model interpretation: a game theoretic approach

May 20, 2021

Attributing a “fair” (for some definition of fair) value to training samples has multiple applications. It can be used to investigate or improve data sources, but it can also help detect outliers and to investigate how certain features and the values thereof influence global model performance. It is also possible to improve model performance: removing points of low value can decrease model error.

Series: Data Valuation

A picture of Miguel

Introduction to simulation-based inference

Dec 17, 2020

Scientists and engineers employ stochastic numerical simulators to model empirically observed phenomena. In contrast to purely statistical models, simulators express scientific principles that provide powerful inductive biases, improve generalization to new data or scenarios and allow for fewer, more interpretable and domain-relevant parameters. Despite these advantages, tuning a simulator’s parameters so that its outputs match data is challenging.

Álvaro Tejero-Cantero

Hamiltonian Monte Carlo Sampling

Dec 3, 2020

Metropolis, Slice or Gibbs sampling tend to be inefficient when applied in high dimensions due to their local random walk behaviour. Hamiltonian Monte Carlo (HMC) was developed around a geometrical understanding of the target distribution, borrowing concepts from physics to generate transitions and exploring the target distribution. Ultimately, moving more rapidly through the target distribution.

Series: Bayesian ML and Probabilistic Programming

Maternus Herold

Bayesian optimal experiment design (2 of 2)

Nov 26, 2020

This is the second of a two talks providing an introduction to Bayesian optimal experimental design (BOED) and how it relates to exploration in reinforcement learning and control. The first part dealt with the theoretical foundations for BOED. This talk completes the topic by presenting an application in control, which was created during my master thesis at TUDa.

Bayesian optimal experiment design (1 of 2)

Nov 19, 2020

These two talks give an introduction to Bayesian optimal experimental design (BOED) and how it relates to exploration in reinforcement learning and control. The first part deals with the theoretical foundations for BOED. Different design types are covered, e.g. space filling designs, alphabetic designs and Bayesian designs. Afterwards it is shown how Bayes' theorem relates to the mutual information (MI) or equally the expected information gain (EIG).

Solving Schrödinger's equation with neural networks

Nov 12, 2020

In this work, we attempt to solve the Time Dependent Schrödinger Equation directly by placing a neural network ansatz on the solution and designing a loss metric based on the constraints imposed by the equation. We show that the method works for simple cases, such as those in 1D or with the free Hamiltonian, but fails in higher dimensions (3D+) or when a complex potential is present.

Series: Simulation and AI

A picture of Omer

Bayesian ML and Probabilistic Programming 3: Variational Inference

Nov 5, 2020

In this talk, we lay the ground for Markov Chain Monte Carlo (MCMC) methods to inferring the posterior distribution, after looking into the limitations posed by the analytical approach. We demonstrate how MCMC works and use it to solve a Bayesian regression problem and introduce concepts related to causal inference. Before doing so, we have a quick tutorial on using Pyro as a probabilistic programming language.

Series: Bayesian ML and Probabilistic Programming

A picture of Faried

Duality in RL and the [*]-DICE Family (part 2)

Oct 29, 2020

The goal of reinforcement learning is to find an optimal policy. Two commonly used classes of methods are i) policy gradient and ii) dynamic programming based methods. In this talk I will describe an alternative solution strategy based on LP duality. It is based on the duality of Q-values and state-action visitations.

A picture of Robert

Bayesian ML and Probabilistic Programming 2: MCMC, Bayesian Regression and Causality

Oct 22, 2020

In this talk, we lay the ground for Markov Chain Monte Carlo (MCMC) methods to inferring the posterior distribution, after looking into the limitations posed by the analytical approach. We demonstrate how MCMC works and use it to solve a Bayesian regression problem and introduce concepts related to causal inference. Before doing so, we have a quick tutorial on using Pyro as a probabilistic programming language.

Series: Bayesian ML and Probabilistic Programming

A picture of Mustafa

Duality in RL and the [*]-DICE Family (part 1)

Oct 15, 2020

The goal of reinforcement learning is to find an optimal policy. Two commonly used classes of methods are i) policy gradient and ii) dynamic programming based methods. In this talk I will describe an alternative solution strategy based on LP duality. It is based on the duality of Q-values and state-action visitations.

A picture of Robert

Join us