50 citations · 151 across the 23 of their papers we have counts for
26 papers
Introduction to Stochastic Differential Equations for Generative Machine Learning: A Variational Perspective
Ole Winther, Paul Jeha, Sander Dieleman +3
The use of ordinary and stochastic differential equations has led to substantial progress in generative machine learning with applications to, for example, image, video and biomole…
Logit Distance Bounds Representational Similarity
Beatrix M. G. Nielsen, Emanuele Marconato, Luigi Gresele +2
For a broad family of discriminative models that includes autoregressive language models, identifiability results imply that if two models induce the same conditional distributions…
Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts
Yasin Esfandiari, Stefan Bauer, Sebastian U. Stich +1
Diffusion models for image generation often exhibit a trade-off between perceptual sample quality and data likelihood: training objectives emphasizing high-noise denoising steps yi…
When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective
Beatrix M. G. Nielsen, Emanuele Marconato, Andrea Dittadi +1
When and why representations learned by different deep neural networks are similar is an active research topic. We choose to address these questions from the perspective of identif…
Minimum-Excess-Work Guidance
Christopher Kolloff, Tobias Höppe, Emmanouil Angelis +4
We propose a regularization framework inspired by thermodynamic work for guiding pre-trained probability flow generative models (e.g., continuous normalizing flows or diffusion mod…
Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations
Shruti Joshi, Andrea Dittadi, Sébastien Lachapelle +1
Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, c…
Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models
Amir Mohammad Karimi Mamaghan, Samuele Papa, Karl Henrik Johansson +2
Object-centric (OC) representations, which model visual scenes as compositions of discrete objects, have the potential to be used in various downstream tasks to achieve systematic…
Diffusion Based Causal Representation Learning
Amir Mohammad Karimi Mamaghan, Andrea Dittadi, Stefan Bauer +2
Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause-effect estimation and the ident…
DiffEnc: Variational Diffusion with a Learned Encoder
Beatrix M. G. Nielsen, Anders Christensen, Andrea Dittadi +1
Diffusion models may be viewed as hierarchical variational autoencoders (VAEs) with two improvements: parameter sharing for the conditional distributions in the generative process…
On the Generalization of Learned Structured Representations
Andrea Dittadi
Despite tremendous progress over the past decade, deep learning methods generally fall short of human-level systematic generalization. It has been argued that explicitly capturing…
Assessing Neural Network Robustness via Adversarial Pivotal Tuning
Peter Ebert Christensen, Vésteinn Snæbjarnarson, Andrea Dittadi +2
The robustness of image classifiers is essential to their deployment in the real world. The ability to assess this resilience to manipulations or deviations from the training data…
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
Cian Eastwood, Andrei Liviu Nicolicioiu, Julius von Kügelgen +4
In representation learning, a common approach is to seek representations which disentangle the underlying factors of variation. Eastwood & Williams (2018) proposed three metrics fo…
Assaying Out-Of-Distribution Generalization in Transfer Learning
Florian Wenzel, Andrea Dittadi, Peter Vincent Gehler +9
Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e.g., calibration, adversarial robustness, algorithmic corruptions, invariance acr…
Diffusion Models for Video Prediction and Infilling
Tobias Höppe, Arash Mehrjou, Stefan Bauer +2
Predicting and anticipating future outcomes or reasoning about missing information in a sequence are critical skills for agents to be able to make intelligent decisions. This requi…
Inductive Biases for Object-Centric Representations in the Presence of Complex Textures
Samuele Papa, Ole Winther, Andrea Dittadi
Understanding which inductive biases could be helpful for the unsupervised learning of object-centric representations of natural scenes is challenging. In this paper, we systematic…
Image Super-Resolution With Deep Variational Autoencoders
Darius Chira, Ilian Haralampiev, Ole Winther +2
Image super-resolution (SR) techniques are used to generate a high-resolution image from a low-resolution image. Until now, deep generative models such as autoregressive models and…
Conditional Generation of Medical Time Series for Extrapolation to Underrepresented Populations
Simon Bing, Andrea Dittadi, Stefan Bauer +1
The widespread adoption of electronic health records (EHRs) and subsequent increased availability of longitudinal healthcare data has led to significant advances in our understandi…
Boxhead: A Dataset for Learning Hierarchical Representations
Yukun Chen, Andrea Dittadi, Frederik Träuble +2
Disentanglement is hypothesized to be beneficial towards a number of downstream tasks. However, a common assumption in learning disentangled representations is that the data genera…
The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents
Andrea Dittadi, Frederik Träuble, Manuel Wüthrich +7
Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level…
Generalization and Robustness Implications in Object-Centric Learning
Andrea Dittadi, Samuele Papa, Michele De Vita +3
The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed represe…
Planning from Pixels in Atari with Learned Symbolic Representations
Andrea Dittadi, Frederik K. Drachmann, Thomas Bolander
Width-based planning methods have been shown to yield state-of-the-art performance in the Atari 2600 domain using pixel input. One successful approach, RolloutIW, represents states…
On the Transfer of Disentangled Representations in Realistic Settings
Andrea Dittadi, Frederik Träuble, Francesco Locatello +5
Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning. While disent…
Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds
Valentin Liévin, Andrea Dittadi, Anders Christensen +1
This paper introduces novel results for the score function gradient estimator of the importance weighted variational bound (IWAE). We prove that in the limit of large (number o…
On Disentangled Representations Learned From Correlated Data
Frederik Träuble, Elliot Creager, Niki Kilbertus +5
The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often…