AIConfPaper
← Search

Matthäus Kleindessner

16 accepted papers

2026

When LLMs get significantly worse: A statistical approach to detect model degradations

Jonas M. Kübler, Kailash Budhathoki, Matthäus Kleindessner, Xiong Zhou, Junming Yin, Ashish Khetan +1
ICLR 2026poster

Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoretically lossless methods and others without accuracy guarantees like quantization. In all of these cases it is crucial to ensure that the model quality has not…

Cited by 0Source ↗code ↗Scholar ↗
2025

Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving

Xinyu Wang, Jonas M. Kübler, Kailash Budhathoki, Yida Wang, Matthäus Kleindessner
NeurIPS 2025poster

When serving a single base LLM with several different LoRA adapters simultaneously, the adapters cannot simply be merged with the base model’s weights as the adapter swapping would create overhead and requests using different adapters could not be batched. Rather, the LoRA computations have to be se…

Cited by 0Source ↗Scholar ↗
2023

Efficient fair PCA for fair representation learning

Matthäus Kleindessner, Michele Donini, Chris Russell, Muhammad Bilal Zafar
AISTATS 2023poster

We revisit the problem of fair principal component analysis (PCA), where the goal is to learn the best low-rank linear approximation of the data that obfuscates demographic information. We propose a conceptually simple approach that allows for an analytic solution similar to standard PCA and can be…

Cited by 18Source ↗PDF ↗code ↗Scholar ↗
2023

When do Minimax-fair Learning and Empirical Risk Minimization Coincide?

Harvineet Singh, Matthäus Kleindessner, Volkan Cevher, Rumi Chunara, Chris Russell
ICML 2023poster

Minimax-fair machine learning minimizes the error for the worst-off group. However, empirical evidence suggests that when sophisticated models are trained with standard empirical risk minimization (ERM), they often have the same performance on the worst-off group as a minimax-trained model. Our work…

Cited by 5Source ↗PDF ↗Scholar ↗
2022

Active Sampling for Min-Max Fairness

Jacob D Abernethy, Pranjal Awasthi, Matthäus Kleindessner, Jamie Morgenstern, Chris Russell, Jie Zhang
ICML 2022spotlight

We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization. The key intuition behind our approach is to use at each timestep a datapoint from the group that is worst off unde…

Cited by 61Source ↗PDF ↗code ↗Scholar ↗
2022

Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks

Michael Lohaus, Matthäus Kleindessner, Krishnaram Kenthapadi, Francesco Locatello, Chris Russell
NeurIPS 2022accept

We show that deep networks trained to satisfy demographic parity often do so through a form of race or gender awareness, and that the more we force a network to be fair, the more accurately we can recover race or gender from the internal state of the network. Based on this observation, we investigat…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2022

Individual Preference Stability for Clustering

Saba Ahmadi, Pranjal Awasthi, Samir Khuller, Matthäus Kleindessner, Jamie Morgenstern, Pattara Sukprasert +1
ICML 2022oral

In this paper, we propose a natural notion of individual preference (IP) stability for clustering, which asks that every data point, on average, is closer to the points in its own cluster than to the points in any other cluster. Our notion can be motivated from several perspectives, including game t…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2022

Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers

Dominik Zietlow, Michael Lohaus, Guha Balakrishnan, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf +1
CVPR 2022poster

Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate. Contrary to this, we find that applying existing fairness approaches to computer v…

Cited by 66PDF ↗Scholar ↗
2022

Pairwise Fairness for Ordinal Regression

Matthäus Kleindessner, Samira Samadi, Muhammad Bilal Zafar, Krishnaram Kenthapadi, Chris Russell
AISTATS 2022poster

We initiate the study of fairness for ordinal regression. We adapt two fairness notions previously considered in fair ranking and propose a strategy for training a predictor that is approximately fair according to either notion. Our predictor has the form of a threshold model, composed of a scoring…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2022

Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

Paul Rolland, Volkan Cevher, Matthäus Kleindessner, Chris Russell, Dominik Janzing, Bernhard Schölkopf +1
ICML 2022oral

This paper demonstrates how to recover causal graphs from the score of the data distribution in non-linear additive (Gaussian) noise models. Using score matching algorithms as a building block, we show how to design a new generation of scalable causal discovery methods. To showcase our approach, we…

Cited by 103Source ↗PDF ↗Scholar ↗
2021

Backward-Compatible Prediction Updates: A Probabilistic Approach

Frederik Träuble, Julius Von Kügelgen, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf, Peter Vincent Gehler
NeurIPS 2021poster

When machine learning systems meet real world applications, accuracy is only one of several requirements. In this paper, we assay a complementary perspective originating from the increasing availability of pre-trained and regularly improving state-of-the-art models. While new improved models develop…

Cited by 20Source ↗PDF ↗Scholar ↗
2020

Equalized odds postprocessing under imperfect group information

Pranjal Awasthi, Matthäus Kleindessner, Jamie Morgenstern
AISTATS 2020poster

Most approaches aiming to ensure a model’s fairness with respect to a protected attribute (such as gender or race) assume to know the true value of the attribute for every data point. In this paper, we ask to what extent fairness interventions can be effective even when only imperfect information ab…

Cited by 112Source ↗PDF ↗code ↗Scholar ↗
2019

Fair k-Center Clustering for Data Summarization

Matthäus Kleindessner, Pranjal Awasthi, Jamie Morgenstern
ICML 2019oral

In data summarization we want to choose $k$ prototypes in order to summarize a data set. We study a setting where the data set comprises several demographic groups and we are restricted to choose $k_i$ prototypes belonging to group $i$. A common approach to the problem without the fairness constrain…

Cited by 219Source ↗PDF ↗code ↗Scholar ↗
2019

Guarantees for Spectral Clustering with Fairness Constraints

Matthäus Kleindessner, Samira Samadi, Pranjal Awasthi, Jamie Morgenstern
ICML 2019oral

Given the widespread popularity of spectral clustering (SC) for partitioning graph data, we study a version of constrained SC in which we try to incorporate the fairness notion proposed by Chierichetti et al. (2017). According to this notion, a clustering is fair if every demographic group is approx…

Cited by 219Source ↗PDF ↗code ↗Scholar ↗