Arrow Research search

Author name cluster

Anders Christensen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers
2 author rows

Possible papers

7

NeurIPS Conference 2025 Conference Paper

NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models

  • Jarren Zhuoran Qiao
  • Feizhi Ding
  • Thomas Dresselhaus
  • Mia Rosenfeld
  • Xiaotian Han
  • Owen Howell
  • Aniketh Iyengar
  • Stephen Opalenski

Biomolecular structure determination is essential to a mechanistic understanding of diseases and the development of novel therapeutics. Machine-learning-based structure prediction methods have made significant advancements by computationally predicting protein and bioassembly structures from sequences and molecular topology alone. Despite substantial progress in the field, challenges remain to deliver structure prediction models to real-world drug discovery. Here, we present NeuralPLexer3 -- a physics-inspired flow-based generative model that achieves state-of-the-art prediction accuracy on key biomolecular interaction types and improves training and sampling efficiency compared to its predecessors and alternative methodologies. Examined through existing and new benchmarks, NeuralPLexer3 excels in areas crucial to structure-based drug design, including blind docking, physical validity, and ligand-induced protein conformational changes.

PDF Details

ICLR Conference 2024 Conference Paper

DiffEnc: Variational Diffusion with a Learned Encoder

  • Beatrix Miranda Ginn Nielsen
  • Anders Christensen
  • Andrea Dittadi
  • Ole Winther

Diffusion models may be viewed as hierarchical variational autoencoders (VAEs) with two improvements: parameter sharing for the conditionals in the generative process and efficient computation of the loss as independent terms over the hierarchy. We consider two changes to the diffusion model that retain these advantages while adding flexibility to the model. Firstly, we introduce a data and depth-dependent mean function in the diffusion process, which leads to a modified diffusion loss. Our proposed framework, DiffEnc, achieves a statistically significant improvement in likelihood on CIFAR-10. Secondly, we let the ratio of the noise variance of the reverse encoder process and the generative process be a free weight parameter rather than being fixed to one. This leads to theoretical insights: For a finite depth hierarchy, the evidence lower bound (ELBO) can be used as an objective for a weighted diffusion loss approach and for optimizing the noise schedule specifically for inference. For the infinite-depth hierarchy, on the other hand, the weight parameter has to be one to have a well-defined ELBO.

Details

TMLR Journal 2023 Journal Article

Addressing caveats of neural persistence with deep graph persistence

  • Leander Girrbach
  • Anders Christensen
  • Ole Winther
  • Zeynep Akata
  • A. Sophia Koepke

Neural Persistence is a prominent measure for quantifying neural network complexity, proposed in the emerging field of topological data analysis in deep learning. In this work, however, we find both theoretically and empirically that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence. Whilst this captures useful information for linear classifiers, we find that no relevant spatial structure is present in later layers of deep neural networks, making neural persistence roughly equivalent to the variance of weights. Additionally, the proposed averaging procedure across layers for deep neural networks does not consider interaction between layers. Based on our analysis, we propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers, which is equivalent to calculating neural persistence on one particular matrix. This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues through standardisation. Code is available at https://github.com/ExplainableML/Deep-Graph-Persistence.

PDF Details

NeurIPS Conference 2020 Conference Paper

Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds

  • Valentin Liévin
  • Andrea Dittadi
  • Anders Christensen
  • Ole Winther

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 $K$ (number of importance samples) one can choose the control variate such that the Signal-to-Noise ratio (SNR) of the estimator grows as $\sqrt{K}$. This is in contrast to the standard pathwise gradient estimator where the SNR decreases as $1/\sqrt{K}$. Based on our theoretical findings we develop a novel control variate that extends on VIMCO. Empirically, for the training of both continuous and discrete generative models, the proposed method yields superior variance reduction, resulting in an SNR for IWAE that increases with $K$ without relying on the reparameterization trick. The novel estimator is competitive with state-of-the-art reparameterization-free gradient estimators such as Reweighted Wake-Sleep (RWS) and the thermodynamic variational objective (TVO) when training generative models.

PDF Details

AAMAS Conference 2010 Conference Paper

Coordination Through Institutional Roles in Robot Collectives

  • Jos
  • eacute; Nuno Pereira
  • Anders Christensen
  • Porf
  • iacute; rio Silva
  • Pedro Lima

In this paper, we demonstrate the benefit of role allocationin a collective of autonomous robots performing a simpletransport task. We demonstrate that, under certain conditions, the performance of the collective can be improvedwhen a subset of the robots assume institutional roles as traffic regulators. The concept of institutional roles is part of ahigh-level approach to the control of multi-robot collectivescalled Institutional Robotics. We compare the institutionalrobotics approach to a swarm robotics approach. Based onresults of experiments in simulation, we conclude that thecoordination provided by the traffic regulating robots improves performance for large collectives, but for small collectives the performance is higher when all robots are directlyinvolved in carrying out the task.

PDF

AAMAS Conference 2010 Conference Paper

Establishing Spatially Targeted Communication in a Heterogeneous Robot Swarm

  • Nithin Mathews
  • Anders Christensen
  • Eliseo Ferrante
  • Rehan O'Grady
  • Marco Dorigo

We consider a heterogeneous swarm consisting of aerial andwheeled robots. We present a system that enables spatiallytargeted communication. Our system enables aerial robots toestablish dedicated communication links with individual wheeledrobots or with selected groups of wheeled robots based on theirposition in the environment. The system does not rely on any form of globalinformation. We show how a spatially targetedone-to-one communication link can be established using a simple LEDand camera based communication modality. We provide a probabilisticmodel of our approach to derive an upper bound on the average timerequired for establishing communication. In simulation, we show thatour approach scales well. Furthermore, we show how our approach can beextended to establish a spatially targeted one-to-many communicationlink between an aerial robot and a specific number of co-locatedwheeled robots. The heterogeneous swarm robotic hardware is currentlyunder development. We therefore demonstrate the proposed approach onan existing multirobot system consisting of only wheeled robots byletting one of the wheeled robots assume the role of an aerial robot.

PDF
v2026.09.13