581 citations · 1.5k across the 65 of their papers we have counts for
30 papers · 1 filter
Symmetry-Informed Causal Partial Identification
Uzair Akbar, Zulfiqar Zaidi, Niki Kilbertus +2
Partial identification (PI) entails estimating bounds on causal effects by encoding different assumptions on data generation as a constrained optimization problem. Such bounds can…
QuadraSHAP: -Exact Shapley Values for Product Games in Logarithmic Parallel Time
Majid Mohammadi, Grigory Reznikov, Pavel Sinitcyn +2
We introduce QuadraSHAP, a method for -exact Shapley computation in product games, cooperative games whose coalition values factorize across players. Given a tolerance ,…
Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration
Chongsheng Zhang, Hao Wang, Zelong Yu +7
Imbalanced data are commonly present in real-world applications. While data synthesis can effectively mitigate data scarcity for rare classes, and LLMs have revolutionized text gen…
Incentive Aware AI Regulations: A Credal Characterisation
Anurag Singh, Julian Rodemann, Rajeev Verma +2
The rapid proliferation of AI applications has intensified debate on effective regulation of these black-box services. Effective regulation must balance two competing goals: (1) de…
An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation
Uzair Akbar, Niki Kilbertus, Hao Shen +2
The technique of data augmentation (DA) is often used in machine learning for regularization purposes to better generalize under i.i.d. settings. In this work, we present a unifyin…
When Do Credal Sets Stabilize? Fixed-Point Theorems for Credal Set Updates
Michele Caprio, Siu Lun Chau, Krikamol Muandet
Many machine learning algorithms rely on iterative updates of uncertainty representations, ranging from variational inference and expectation-maximization, to reinforcement learnin…
Exact Shapley Attributions in Quadratic-time for FANOVA Gaussian Processes
Majid Mohammadi, Krikamol Muandet, Ilaria Tiddi +2
Shapley values are widely recognized as a principled method for attributing importance to input features in machine learning. However, the exact computation of Shapley values scale…
When Shift Happens - Confounding Is to Blame
Abbavaram Gowtham Reddy, Celia Rubio-Madrigal, Rebekka Burkholz +1
Distribution shifts introduce uncertainty that undermines the robustness and generalization capabilities of machine learning models. While conventional wisdom suggests that learnin…
Amortized Linear-time Exact Shapley Value for Product-Kernel Methods
Majid Mohammadi, Siu Lun Chau, Krikamol Muandet
Kernel methods are widely used in machine learning and statistics for their flexibility and expressive power, yet their black-box nature limits adoption in high-stakes applications…
Truthful Elicitation of Imprecise Forecasts
Anurag Singh, Siu Lun Chau, Krikamol Muandet
The quality of probabilistic forecasts is crucial for decision-making under uncertainty. While proper scoring rules incentivize truthful reporting of precise forecasts, they fall s…
Domain Generalisation via Imprecise Learning
Anurag Singh, Siu Lun Chau, Shahine Bouabid +1
Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e.g.,…
Robust Feature Inference: A Test-time Defense Strategy using Spectral Projections
Anurag Singh, Mahalakshmi Sabanayagam, Krikamol Muandet +1
Test-time defenses are used to improve the robustness of deep neural networks to adversarial examples during inference. However, existing methods either require an additional train…
On the Relationship Between Explanation and Prediction: A Causal View
Amir-Hossein Karimi, Krikamol Muandet, Simon Kornblith +2
Being able to provide explanations for a model's decision has become a central requirement for the development, deployment, and adoption of machine learning models. However, we are…
Learning Counterfactually Invariant Predictors
Francesco Quinzan, Cecilia Casolo, Krikamol Muandet +2
Notions of counterfactual invariance (CI) have proven essential for predictors that are fair, robust, and generalizable in the real world. We propose graphical criteria that yield…
Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions
Heiner Kremer, Jia-Jie Zhu, Krikamol Muandet +1
Important problems in causal inference, economics, and, more generally, robust machine learning can be expressed as conditional moment restrictions, but estimation becomes challeng…
Gated Domain Units for Multi-source Domain Generalization
Simon Föll, Alina Dubatovka, Eugen Ernst +7
The phenomenon of distribution shift (DS) occurs when a dataset at test time differs from the dataset at training time, which can significantly impair the performance of a machine…
AutoML Two-Sample Test
Jonas M. Kübler, Vincent Stimper, Simon Buchholz +2
Two-sample tests are important in statistics and machine learning, both as tools for scientific discovery as well as to detect distribution shifts. This led to the development of m…
(Im)possibility of Collective Intelligence
Krikamol Muandet
Modern applications of AI involve training and deploying machine learning models across heterogeneous and potentially massive environments. Emerging diversity of data not only brin…
Instrument Space Selection for Kernel Maximum Moment Restriction
Rui Zhang, Krikamol Muandet, Bernhard Schölkopf +1
Kernel maximum moment restriction (KMMR) recently emerges as a popular framework for instrumental variable (IV) based conditional moment restriction (CMR) models with important app…
Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction
Afsaneh Mastouri, Yuchen Zhu, Limor Gultchin +5
We address the problem of causal effect estimation in the presence of unobserved confounding, but where proxies for the latent confounder(s) are observed. We propose two kernel-bas…
A Witness Two-Sample Test
Jonas M. Kübler, Wittawat Jitkrittum, Bernhard Schölkopf +1
The Maximum Mean Discrepancy (MMD) has been the state-of-the-art nonparametric test for tackling the two-sample problem. Its statistic is given by the difference in expectations of…
Instrumental Variable Regression via Kernel Maximum Moment Loss
Rui Zhang, Masaaki Imaizumi, Bernhard Schölkopf +1
We investigate a simple objective for nonlinear instrumental variable (IV) regression based on a kernelized conditional moment restriction (CMR) known as a maximum moment restricti…
Learning Kernel Tests Without Data Splitting
Jonas M. Kübler, Wittawat Jitkrittum, Bernhard Schölkopf +1
Modern large-scale kernel-based tests such as maximum mean discrepancy (MMD) and kernelized Stein discrepancy (KSD) optimize kernel hyperparameters on a held-out sample via data sp…
A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings
Junhyung Park, Krikamol Muandet
We present an operator-free, measure-theoretic approach to the conditional mean embedding (CME) as a random variable taking values in a reproducing kernel Hilbert space. While the…