Search Results for author:
Found 41 papers, 13 papers with code
NetGAN without GAN: From Random Walks to Low-Rank Approximations
In this paper, we investigate the implicit bias of NetGAN.
Statistics without Interpretation: A Sober Look at Explainable Machine Learning
In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used.
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
In this paper, we show that the smoothness of the estimators, and not the dimension, is the key: benign overfitting is possible if and only if the estimator's derivatives are large enough.
ChatGPT Participates in a Computer Science Exam
We asked ChatGPT to participate in an undergraduate computer science exam on ''Algorithms and Data Structures''.
AI for Science: An Emerging Agenda
This report summarises the discussions from the seminar and provides a roadmap to suggest how different communities can collaborate to deliver a new wave of progress in AI and its application for scientific discovery.
Pitfalls of Climate Network Construction: A Statistical Perspective
Network-based analyses of dynamical systems have become increasingly popular in climate science.
Relating graph auto-encoders to linear models
In our work, we prove that the solution space induced by graph auto-encoders is a subset of the solution space of a linear map.
A Consistent Estimator for Confounding Strength
Regression on observational data can fail to capture a causal relationship in the presence of unobserved confounding.
From Shapley Values to Generalized Additive Models and back
We then show that $n$-Shapley Values, as well as the Shapley Taylor- and Faith-Shap interaction indices, recover GAMs with interaction terms up to order $n$.
The Manifold Hypothesis for Gradient-Based Explanations
We propose a necessary criterion: their feature attributions need to be aligned with the tangent space of the data manifold.
Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference
By reframing the problem in terms of incompatible conditional distributions we arrive at a natural solution: the Gibbs prior.
Interpolation and Regularization for Causal Learning
If the confounding strength is negative, causal learning requires weaker regularization than statistical learning, interpolators can be optimal, and the optimal regularization can even be negative.
Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts
In this paper, we combine legal, philosophical and technical arguments to show that post-hoc explanation algorithms are unsuitable to achieve the law's objectives.
Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models
Despite the ubiquity of kernel-based clustering, surprisingly few statistical guarantees exist beyond settings that consider strong structural assumptions on the data generation process.
Specialists Outperform Generalists in Ensemble Classification
We explicitly construct the individual classifiers that attain the upper and lower bounds: specialists and generalists.
Looking Deeper into Tabular LIME
As an example, for linear functions we show that LIME has the desirable property to provide explanations that are proportional to the coefficients of the function to explain and to ignore coordinates that are not used by the function to explain.
A Bandit Model for Human-Machine Decision Making with Private Information and Opacity
A lower bound quantifies the worst-case hardness of optimally advising a decision maker who is opaque or has access to private information.
Clustering with Tangles: Algorithmic Framework and Theoretical Guarantees
Given a collection of cuts of any dataset, tangles aggregate these cuts to point in the direction of a dense structure.
Explaining the Explainer: A First Theoretical Analysis of LIME
We derive closed-form expressions for the coefficients of the interpretable model when the function to explain is linear.
Insights into Ordinal Embedding Algorithms: A Systematic Evaluation
However, there does not exist a fair and thorough assessment of these embedding methods and therefore several key questions remain unanswered: Which algorithms perform better when the embedding dimension is constrained or few triplet comparisons are available?
LARGE SCALE REPRESENTATION LEARNING FROM TRIPLET COMPARISONS
This problem has been studied in a sub-community of machine learning by the name "Ordinal Embedding".
Estimation of perceptual scales using ordinal embedding
We propose to use ordinal embedding methods from machine learning to estimate the scaling function from the relative judgments.
Uncertainty Estimates for Ordinal Embeddings
To investigate objects without a describable notion of distance, one can gather ordinal information by asking triplet comparisons of the form "Is object $x$ closer to $y$ or is $x$ closer to $z$?"
Comparison-Based Framework for Psychophysics: Lab versus Crowdsourcing
In this paper we study whether the use of comparison-based (ordinal) data, combined with machine learning algorithms, can boost the reliability of crowdsourcing studies for psychophysics, such that they can achieve performance close to a lab experiment.
When do random forests fail?
As a consequence, even highly randomized trees can lead to inconsistent forests if no subsampling is used, which implies that some of the commonly used setups for random forests can be inconsistent.
Measures of distortion for machine learning
We can show both in theory and in experiments that it satisfies all desirable properties and is a better candidate to evaluate distortion in the context of machine learning.
Practical methods for graph two-sample testing
Hypothesis testing for graphs has been an important tool in applied research fields for more than two decades, and still remains a challenging problem as one often needs to draw inference from few replicates of large graphs.
Foundations of Comparison-Based Hierarchical Clustering
We address the classical problem of hierarchical clustering, but in a framework where one does not have access to a representation of the objects or their pairwise similarities.
Boosting for Comparison-Based Learning
We consider the problem of classification in a comparison-based setting: given a set of objects, we only have access to triplet comparisons of the form "object $x_i$ is closer to object $x_j$ than to object $x_k$."
Comparison-Based Random Forests
Assume we are given a set of items from a general metric space, but we neither have access to the representation of the data nor to the distances between data points.
Design and Analysis of the NIPS 2016 Review Process
Neural Information Processing Systems (NIPS) is a top-tier annual conference in machine learning.
Two-sample Hypothesis Testing for Inhomogeneous Random Graphs
Given a population of $m$ graphs from each model, we derive minimax separation rates for the problem of testing $P=Q$ against $d(P, Q)>\rho$.
Two-Sample Tests for Large Random Graphs Using Network Statistics
We consider a two-sample hypothesis testing problem, where the distributions are defined on the space of undirected graphs, and one has access to only one observation from each model.
Comparison Based Nearest Neighbor Search
We consider machine learning in a comparison-based setting where we are given a set of points in a metric space, but we have no access to the actual distances between the points.
Kernel functions based on triplet comparisons
Given only information in the form of similarity triplets "Object A is more similar to object B than to object C" about a data set, we propose two ways of defining a kernel function on the data set.
Lens depth function and k-relative neighborhood graph: versatile tools for ordinal data analysis
In recent years it has become popular to study machine learning problems in a setting of ordinal distance information rather than numerical distance measurements.
Peer Grading in a Course on Algorithms and Data Structures: Machine Learning Algorithms do not Improve over Simple Baselines
Peer grading is the process of students reviewing each others' work, such as homework submissions, and has lately become a popular mechanism used in massive open online courses (MOOCs).
Consistent procedures for cluster tree estimation and pruning
For a density $f$ on ${\mathbb R}^d$, a {\it high-density cluster} is any connected component of $\{x: f(x) \geq \lambda\}$, for some $\lambda > 0$.
Density estimation from unweighted k-nearest neighbor graphs: a roadmap
Consider an unweighted k-nearest neighbor graph on n points that have been sampled i. i. d.
A Tutorial on Spectral Clustering
In recent years, spectral clustering has become one of the most popular modern clustering algorithms.
