I am a PhD student at the Max Planck Institute for Intelligent Systems, focusing on collective action in ML and novel generative modeling frameworks. My research explores how individuals can coordinate data modifications to influence machine learning outcomes, alongside the creation of new generative modeling frameworks. I am passionate about the interaction of machine learning with the real world, from what we can learn about the world using ML, to how society and ML can influence each other.
-
2025-12-06
Our work on collective action for fairness in machine learning was selected to be an oral presentation at the Algorithmic Collective Action workshop in NeurIPS 25!
-
2025-11-14
Our preprint Adaptive Symmetrization of the KL Divergence is now available on arXiv.
-
2025-10-17
I was selected as a top reviewer for Neurips 2025!
-
2025-08-22
Our preprint Fairness for the People, by the People: Minority Collective Action is now available on arXiv.
-
2025-07-27
I am giving a non-technical talk at Tübingen Days of Digital Freedom 2025 event about collective action for fairness in machine learning.
-
2025-04-01
Visiting École Polytechnique in Paris for 3 months to work with Luiz Chamon.
-
2024-10-01
Visiting Copenhagen university for 3 months to work with Amartya Sanyal.
- Adversarial Likelihood Estimation With One-Way Flows2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024paper
abstract
Generative Adversarial Networks (GANs) can produce high-quality samples, but do not provide an estimate of the probability density around the samples. However, it has been noted that maximizing the log-likelihood within an energy-based setting can lead to an adversarial framework where the discriminator provides unnormalized density (often called energy). We further develop this perspective, incorporate importance sampling, and show that 1) Wasserstein GAN performs a biased estimate of the partition function, and we propose instead to use an unbiased estimator; and 2) when optimizing for likelihood, one must maximize generator entropy. This is hypothesized to provide a better mode coverage. Different from previous works, we explicitly compute the density of the generated samples. This is the key enabler to designing an unbiased estimator of the partition function and computation of the generator entropy term. The generator density is obtained via a new type of flow network, called one-way flow network, that is less constrained in terms of architecture, as it does not require a tractable inverse function. Our experimental results show that our method converges faster, produces comparable sample quality to GANs with similar architecture, successfully avoids over-fitting to commonly used datasets and produces smooth low-dimensional latent representations of the training data. - The Role of Learning Algorithms in Collective ActionProceedings of the 41st International Conference on Machine Learning, 2024paper
abstract
Collective action in machine learning is the study of the control that a coordinated group can have over machine learning algorithms. While previous research has concentrated on assessing the impact of collectives against Bayes (sub-)optimal classifiers, this perspective is limited in that it does not account for the choice of learning algorithm. Since classifiers seldom behave like Bayes classifiers and are influenced by the choice of learning algorithms along with their inherent biases, in this work we initiate the study of how the choice of the learning algorithm plays a role in the success of a collective in practical settings. Specifically, we focus on distributionally robust optimization (DRO), popular for improving a worst group error, and on the ubiquitous stochastic gradient descent (SGD), due to its inductive bias for "simpler" functions. Our empirical results, supported by a theoretical foundation, show that the effective size and success of the collective are highly dependent on properties of the learning algorithm. This highlights the necessity of taking the learning algorithm into account when studying the impact of collective action in machine learning. - Model-Based Tracking of Fruit Flies in Free FlightInsects, 2022paper
abstract
Insect flight is a complex interdisciplinary phenomenon. Understanding its multiple aspects, such as flight control, sensory integration, physiology and genetics, often requires the analysis of large amounts of free flight kinematic data. Yet, one of the main bottlenecks in this field is automatically and accurately extracting such data from multi-view videos. Here, we present a model-based method for the pose estimation of free-flying fruit flies from multi-view high-speed videos. To obtain a faithful representation of the fly with minimum free parameters, our method uses a 3D model that includes two new aspects of wing deformation: A non-fixed wing hinge and a twisting wing surface. The method is demonstrated for free and perturbed flight. Our method does not use prior assumptions on the kinematics apart from the continuity of the wing pitch angle. Hence, this method can be readily adjusted for other insect species.