Author name cluster

Philipp Geiger

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

TMLR Journal 2022 Journal Article

Fail-Safe Adversarial Generative Imitation Learning

Philipp Geiger
Christoph-Nikolas Straehle

For flexible yet safe imitation learning (IL), we propose theory and a modular method, with a safety layer that enables a closed-form probability density/gradient of the safe generative continuous policy, end-to-end generative adversarial training, and worst-case safety guarantees. The safety layer maps all actions into a set of safe actions, and uses the change-of-variables formula plus additivity of measures for the density. The set of safe actions is inferred by first checking safety of a finite sample of actions via adversarial reachability analysis of fallback maneuvers, and then concluding on the safety of these actions' neighborhoods using, e.g., Lipschitz continuity. We provide theoretical analysis showing the robustness advantage of using the safety layer already during training (imitation error linear in the horizon) compared to only using it at test time (up to quadratic error). In an experiment on real-world driver interaction data, we empirically demonstrate tractability, safety and imitation performance of our approach.

PDF Details

AAAI Conference 2021 Conference Paper

Learning Game-Theoretic Models of Multiagent Trajectories Using Implicit Layers

Philipp Geiger
Christoph-Nikolas Straehle

For prediction of interacting agents’ trajectories, we propose an end-to-end trainable architecture that hybridizes neural nets with game-theoretic reasoning, has interpretable intermediate representations, and transfers to downstream decision making. It uses a net that reveals preferences from the agents’ past joint trajectory, and a differentiable implicit layer that maps these preferences to local Nash equilibria, forming the modes of the predicted future trajectory. Additionally, it learns an equilibrium refinement concept. For tractability, we introduce a new class of continuous potential games and an equilibrium-separating partition of the action space. We provide theoretical results for explicit gradients and soundness. In experiments, we evaluate our approach on two real-world data sets, where we predict highway drivers’ merging trajectories, and on a simple decision-making transfer task.

PDF Details

AAAI Conference 2020 Conference Paper

Causal Transfer for Imitation Learning and Decision Making under Sensor-Shift

Jalal Etesami
Philipp Geiger

Learning from demonstrations (LfD) is an efﬁcient paradigm to train AI agents. But major issues arise when there are differences between (a) the demonstrator’s own sensory input, (b) our sensors that observe the demonstrator and (c) the sensory input of the agent we train. In this paper, we propose a causal model-based framework for transfer learning under such “sensor-shifts”, for two common LfD tasks: (1) inferring the effect of the demonstrator’s actions and (2) imitation learning. First we rigorously analyze, on the population-level, to what extent the relevant underlying mechanisms (the action effects and the demonstrator policy) can be identiﬁed and transferred from the available observations together with prior knowledge of sensor characteristics. And we device an algorithm to infer these mechanisms. Then we introduce several proxy methods which are easier to calculate, estimate from ﬁnite data and interpret than the exact solutions, alongside theoretical bounds on their closeness to the exact ones. We validate our two main methods on simulated and semi-real world data.

PDF Details

UAI Conference 2019 Conference Paper

Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory

Philipp Geiger
Michel Besserve
Justus Winkelmann
Claudius Proissl
Bernhard Schölkopf

We study data-driven assistants that provide congestion forecasts to users of shared facilities (roads, cafeterias, etc.), to support coordination between them, and increase efficiency of such collective systems. Key questions are: (1) when and how much can (accurate) predictions help for coordination, and (2) which assistant algorithms reach optimal predictions? First we lay conceptual ground for this setting where user preferences are a priori unknown and predictions influence outcomes. Addressing (1), we establish conditions under which self-fulfilling prophecies, i. e. , “perfect” (probabilistic) predictions of what will happen, solve the coordination problem in the gametheoretic sense of selecting a Bayesian Nash equilibrium (BNE). Next we prove that such prophecies exist even in large-scale settings where only aggregated statistics about users are available. This entails a new (nonatomic) BNE existence result. Addressing (2), we propose two assistant algorithms that sequentially learn from users’ reactions, together with optimality/ convergence guarantees. We validate one of them in a large real-world experiment.

Details

ICML Conference 2015 Conference Paper

Causal Inference by Identification of Vector Autoregressive Processes with Hidden Components

Philipp Geiger
Kun Zhang 0001
Bernhard Schölkopf
Mingming Gong
Dominik Janzing

A widely applied approach to causal inference from a time series X, often referred to as “(linear) Granger causal analysis”, is to simply regress present on past and interpret the regression matrix \hatB causally. However, if there is an unmeasured time series Z that influences X, then this approach can lead to wrong causal conclusions, i. e. , distinct from those one would draw if one had additional information such as Z. In this paper we take a different approach: We assume that X together with some hidden Z forms a first order vector autoregressive (VAR) process with transition matrix A, and argue why it is more valid to interpret A causally instead of \hatB. Then we examine under which conditions the most important parts of A are identifiable or almost identifiable from only X. Essentially, sufficient conditions are (1) non-Gaussian, independent noise or (2) no influence from X to Z. We present two estimation algorithms that are tailored towards conditions (1) and (2), respectively, and evaluate them on synthetic and real-world data. We discuss how to check the model using X.

Details

ICML Conference 2015 Conference Paper

Discovering Temporal Causal Relations from Subsampled Data

Mingming Gong
Kun Zhang 0001
Bernhard Schölkopf
Dacheng Tao
Philipp Geiger

Granger causal analysis has been an important tool for causal analysis for time series in various fields, including neuroscience and economics, and recently it has been extended to include instantaneous effects between the time series to explain the contemporaneous dependence in the residuals. In this paper, we assume that the time series at the true causal frequency follow the vector autoregressive model. We show that when the data resolution becomes lower due to subsampling, neither the original Granger causal analysis nor the extended one is able to discover the underlying causal relations. We then aim to answer the following question: can we estimate the temporal causal relations at the right causal frequency from the subsampled data? Traditionally this suffers from the identifiability problems: under the Gaussianity assumption of the data, the solutions are generally not unique. We prove that, however, if the noise terms are non-Gaussian, the underlying model for the high frequency data is identifiable from subsampled data under mild conditions. We then propose an Expectation-Maximization (EM) approach and a variational inference approach to recover temporal causal relations from such subsampled data. Experimental results on both simulated and real data are reported to illustrate the performance of the proposed approaches.

Details

UAI Conference 2014 Conference Paper

Estimating Causal Effects by Bounding Confounding

Philipp Geiger
Dominik Janzing
Bernhard Schölkopf

Assessing the causal effect of a treatment variable X on an outcome variable Y is usually difficult due to the existence of unobserved common causes. Without further assumptions, observed dependences do not even prove the existence of a causal effect from X to Y. It is intuitively clear that strong statistical dependences between X and Y do provide evidence for X influencing Y if the influence of common causes is known to be weak. We propose a framework that formalizes effect versus confounding in various ways and derive upper/lower bounds on the effect in terms of a priori given bounds on confounding. The formalization includes information theoretic quantities like information flow and causal strength, as well as other common notions like effect of treatment on the treated (ETT). We discuss several scenarios where upper bounds on the strength of confounding can be derived. This justifies to some extent human intuition which assumes the presence of causal effect when strong (e. g. close to deterministic) statistical relations are observed.

Details