About me

I do machine learning and computer vision research, where I work with geometric models of observed data. The research tend to follow two directions: use geometric constructions to design models, or model constraints on data using geometry. Check the publications for more specific examples, and don't hesitate to get in touch.

News and Updates

September 29, 2021. Cong's amazing work on energy-based models will appear at this years NeurIPS. We'll get a PDF online soon as it really is work worth sharing. Very exciting!

August 15, 2021. Uploaded the camera ready version of Frederik's upcoming ICCV paper on the Bayesian triplet loss. This notion of distributions over distances opens so many doors -- very exciting!

July 16, 2021. Humbling news: our paper at R:SS got the best student paper award. After years of working on random geometries it's really rewarding to see the theory being put to real use, and it's nice that others see value as well.

July 16, 2021. LogML is over. The organizers did a fantastic job, and I had great fun meeting the students in my team. Such a cool crowd!

July 16, 2021. Medical Xpress is covering Jeppe's paper in Cancers. It's a good read!

July 6, 2021. We have new PhD openings in the MLLS center.

June 25, 2021. I had fun speaking at DiffCVML about identifiability. Such a cool meeting!

June 18, 2021. Jeppe's work on sTIL scoring is out! This is the first time an algorithm adheres to TIL working group guidelines, and results so far are as good as one could hope for. I look forward to seeing Visiopharm put this into production :-)

May 11, 2021. It's official: I'm a roboticist :-) Hadi's paper on geometry for robot learning has been accepted for R:SS. Really awesome to see a robot arm flying around according to geodesics on learned random manifolds!

May 9, 2021. Martin's fantastic GP-LVM paper got accepted to ICML. I think of this as 'probabilistic Isomap with curvature' (yes, ordinary Isomap does not capture curvature).

May 9, 2021. Jakob's work on out-of-distribution detection in hierachical VAEs got accepted to ICML. Some neat insights into how hierachical representations mess with our intution.

April 9, 2021. Illustreret Videnskab (Science Illustrated) is running a profile interview with me (in Danish).

April 8, 2021. I gave a talk in Johan's group at KU Leuven. Some of the thoughest and most well-thoughout questions I have met in a while. I really enjoyed that (really wished it hadn't been virtual).

February 22, 2021. Nicki defended his thesis. What a show! I am so grateful that Nicki is sticking around for a while longer :-)

February 18, 2021. The lockdown has taken my time, resulting in no updates to this site. Fortunately, I work with people that manage to be productive even when I'm not, so a few updates are still in order. (1) One current and one former PhD student managed to produce a baby -- Yay, there's still hope for humanity :-) (2) Georgios' paper got accepted to AISTATS -- amazing! (3) I'm part of a newly funded research center on basic machine learning research in life science -- absolutely amazing. Consequently, new positions will be made available.

December 11, 2020. I had great fun at the NeurIPS workshop on differential geometry -- fantastic event! I even got to join the army :-)

December 7, 2020. Nicki, myself and Wouter have a new paper out on how to reason about protein representations. The experiments showing links between Riemannian representations and evolutionary developments are still blowing my mind!

November 27, 2020. Martin defended his thesis. Overwhelming and emotional! A fantastic show from a fantastic thinker! Thankfully, I get to keep him for a little while longer. Thanks to Carl Henrik, Arno and Jes for "the attack" :-)

November 26, 2020. Frederik put out a new preprint on a Bayesian treatment of image retrieval. Super cool stuff with an elegant likelihood and priors that actually correspond to state-of-the-art engineering tricks. Nice!

June 15, 2020. Frederik and I wrote up some thoughts on the societal impact of proprietary maps (Google maps, etc) and they might end up increasing global inequality. This is based on the bias we observe in visual mapping. The English version is now online.

July 8, 2020. Jeppe's paper on evaluating current UQ techniques for deep learning was accepted at MICCAI 2020. Not as bleak an outlook as I would have expected, but still pretty terrible.

June 23, 2020. Martin and I released a preprint of what I think of as "Isomap with curvature". This is so cool!

June 15, 2020. Frederik and I wrote up some thoughts on the societal impact of proprietary maps (Google maps, etc) and they might end up increasing global inequality. This is based on the bias we observe in visual mapping. Anyway, the write-up is available (in Danish; sorry we're working on getting the English version out) at videnskab.dk.

June 8, 2020. A bunch of us are organizing an IROS workshop on the interplay of robotics and geometry. We don't know if it will be physical or virtual, but we know that it will be fun -- so do join us :-)

June 1, 2020. Dimitris' paper on geometric priors for VAEs got accepted at ICML. I look forward to sharing the camera-ready as the reviewers had excellent suggestions -- thanks!

May 21, 2020. Uploaded the final version of Rudra's Grassmann average paper; this will eventually appear in PAMI.

May 1, 2020. First day that the team is without David. Sad to see him go, but happy that he moved to a permanent position at RISE. You'll be missed, my friend!

April 28, 2020. Frederik's CVPR paper is now finally online. This is really cool stuff; check out the Mapillary blog or go download the data.

April 28, 2020. Pola put out a new preprint on learned data augmentation. In my book, this is the most elegant formulation of data augmentation available. Not only that, it's also easy to implement and actually works :-)

February 24, 2020. Frederik's CVPR paper is on the magic list of accepted papers. Amazing work; I look forward to sharing the camera ready!

February 24, 2020. Dimitris put out a new preprint on sensible priors for VAEs. In my view, this is an essential step needed to have well-defined models, which in turn will lead to interpretability, disentanglement, causal models, and much more. I'm so excited, and I just can't hide it!

January 10, 2020. Starting first of January, 2020, I have been upgraded to full professor here at DTU. I'm really excited that DTU decided to upgrade me while I am on parental leave; this very well summarize DTU as a working environment!

December 28, 2019. I am on parental leave until summer 2020. While I expect to read e-mail from time to time, I may not reply as fast as I otherwise would. If it's urgent, then say so explicitly in the e-mail subject.

December 19, 2019. Sitting in Helsinki airport on my way home from the Deep Structures workshop where I talked about the stuff only Bayes should do. Absolutely fantastic meeting, and a much needed change from NeurIPS.

December 13, 2019. Packing up and heading home from NeurIPS where Martin, Nicki and I presented two posters. Fun and exciting, but the meeting sure is getting crowded.

December 5, 2019. Martin, Nicki and myself wrote a short piece on the importance of uncertainty in AI for the Danish science communication platform 'Videnskab.dk'. If you read Danish, then you might enjoy this!

November 27, 2019. I visited the Geometry and Topologi group at Aarhus University to talk about random manifolds. Exciting discussions about 'reach' and related topics!

November 24, 2019. Alfredo posted a preprint of the work on parallel QR solvers. We're hoping these techniques can speed up geodesic computations in the near future.

November 20, 2019. I gave a talk about the stuff only Bayes should do at the Danish Society for Theoretical Statistics. Fantastic set of people!

November 7, 2019. The camera-ready of our variance paper at NeurIPS is now online. Sweet stuff; enjoy!

November 7, 2019. Two new open positions (1 Phd; 1 postdoc). Read more here if you're interested.

September 26, 2019. Based on feedback collected along the way, I have now updated the manuscript of what only Bayes should do. Enjoy!

September 6, 2019. Two papers accepted to NeurIPS: one on UQ and another on disentanglement. The papers still need to be updated for the camera-ready.

September 6, 2019. Returned from some hectic days at DALI, where I gave two talks (on operational representation learning and the stuff only Bayes should do) and presented a poster. To add to the excitements, I had a baby strapped to my chest most of the time :-)

August 22, 2019. New preprint online. Here David provide rather tight approximation bounds on the expected length of a curve on a random manifold. Pretty exciting stuff as it justifies an approximation we keep on using :-)

August 13, 2019. Talked about operational representation learning at the DTU+DIKU Summer School on Generative Models. Good fun!

July 15, 2019. I got sick and tired of typing plt.plot(x.detach().cpu().numpy(), y.detach().cpu().numpy(), color="green"), so I put together a little pyplot wrapper that converts torch tensors automatically to numpy arrays. Here's the code; let me know if you have smarter ways of getting the same result!

July 11, 2019. Gave a talk about the stuff Only Bayes can do at AIP 2019. Interesting meeting; always great to make friends in new communities :-)

July 4, 2019. Slowly getting back into action after the birth of our second daughter. Uploaded two exciting preprint: one on UQ and another on disentanglement. Enjoy!

April 5, 2019. I gave a talk at the DIKU AI seminar on the stuff Only Bayes can do. Great discussions, and free beer...

April 3, 2019. Just returned from a great Villum meeting on equality, diversity and inclusiveness in science. Having a four year old daughter creates a bit of a ticking clock for me on this topic... scary!

March 29, 2019. Returned from a thrilling meeting with the WEF Young Scientists in London. Fantastic improv and an amazing show of communication from Emma and Camilla. Wow!

March 24, 2019. The code for Georgios's AISTATS paper is finally online.

January 31, 2019. Today is Georgios's last day as a PhD student. Excellent thesis submitted. Very emotional! Good luck m'boy -- you will be missed!

January 22, 2019. I have now uplodaed the camera-ready version of Georgios's AISTATS paper. Enjoy!

January 2, 2019. Returned to the office after an offline-holiday to see two papers accepted at AISTATS. Yay! Excellent work by Georgios and Anton. I'll post the camera-ready papers when they're ready :-)

November 13, 2018. Visited Prowler.io to see their fantastic work. Also talked about the stuff that Only Bayes can do. Great fun!

October 24, 2018. The ERC just posted a short video interview with me on the key issues of ML. The actual interview was repeatedly interupted by people shaking cow bells (that's a Davos thing); hopefully, you can't see that in the final take :-)

October 8, 2018. Last week I had a one-week-intern from 9th grade in the lab; made him solve linear regression with grid search. Interesting reminder that people who are not familiar with derivatives would never think of minimizing sum-of-squares (he naturally arrived at sum-of-absolute-values)...

September 24, 2018. I am back from the "Summer Davos" meeting in the World Economic Forum. Quite intense. I think the research community could learn quite a lot on how to structure a meeting to focus on "discussion" rather than "presentation". More on this later...

August 24, 2018. I talked about data augmentation and CPAB at our machine learning summer school. Enter the dragon...

July 14, 2018. The second installment of GiMLi is now over. What a fantastic show -- thanks to all involved in making this happen!

July 11, 2018. I presented my work on the Riemannian normal distributions on spheres at Fusion. Excellent meeting on directional statistics!

June 21, 2018. Nicki and I presented the diffeomorphic spatial transformer network at CVPR. Excellent discussions; much fun!

June 14, 2018. New preprint online (it's NIPS formatted, but hasn't been submitted) on why uncertainty quantification is essential for manifold/representation learning. That's at least the case, when you approach the problem from a differential geometric viewpoint, but I expect that the underlying message is generally true.

June 4, 2018. I put up a short note on the non-central Nakagami distribution as I couldn't find information on this distribution elsewhere.

May 29, 2018. Anton posted his work on wrapped GP-LVMs on manifolds to arXiv. Its great to have some nonlinear (i.e. non-geodesic) tools for modeling on non-linear spaces!

May 14, 2018. It seems I was nominated for teacher-of-the-year award. Thanks to whoever nominated me :-)

March 24, 2018. I have uploaded the camera-ready of our work on diffeomorphic statial transformer nets. If you don't need the flexibility of CPAB, then at least take the matrix exponential of your affine transformation matrix.

March 2, 2018. I finally got around to uploading the abstract for my Oberwolfach talk. This contain no new results, but the derivations are more explicit than what we have presented elsewhere.

February 19, 2018. Nicki's paper on spatial transformer nets appears to be on the magic list of accepted CVPR papers -- yay! I'll link to the PDF once we have finished the camera-ready version.

January 30, 2018. Georgios, Lars, and my work on the geometry of latent variable models has been accepted at ICLR. Fun stuff -- I hope to discuss it with you at the venue :-)

January 26, 2018. I talked about the geometry of latent variable models (random Riemannian metrics to the rescue!) at the Oberwolfach workshop on Statistics for Data with Geometric Structure (check link for a picture of me and Agnes).

January 16, 2018. I gave a seminar at University of Oxford on data augmentation (c.f. the dragon), followed by Justin's viva -- great stuff on GP arc lengths!

November 10, 2017. Machine Learning & Molecules is over for now -- what an amazing ride! Thanks to all 16 amazing speakers and to the Bard for final disruptions!

November 1, 2017. Some of our latest results on deep generative models are now on arXiv. Lovely to see how geometry vastly improves the usefulness of latent variable models.

September 6, 2017. The European Research Council (ERC) has been generous enough to award me a starting grant. Humbling and awesome :-)

August 30, 2017. Lectured on metric learning at our yearly machine learning summer school. Always fun when people realize that metric learning is "easier" (for a suitable definition of "easy") in infinite dimensions...

July 31, 2017. Georgios, Lars, and I have a new paper at GSI on how to estimate the parameters of the LAND using maximum likelihood. Check it out!

May 5, 2017. I gave a seminar at the statistics department at KU on data augmentation (c.f. the dragon). Super curious audience plus chocolate -- can't be much better than that :-)

April 28, 2017. I was the "opening act" in Jes's seminar series on machine learning at ITU. Great group! and free pizza (yay!)

April 20, 2017. Jeppe Thagaard came in on a 5th place at the Camelyon17 challenge at ISBI. Great stuff on data augmentation!

March 2, 2017. Yesterday was my first day as an associate professor here at CogSys. Yesterday I was also home sick with a delightful fever; I sure hope there's no link between these event...

February 27, 2017. The extension of Grassmann Averages to higher dimensional subspaces has been accepted to CVPR. The submitted version is on arXiv -- I'll link to the camera ready when it's ready!

January 25, 2017. I'm visiting Bodo's group -- so much impressive stuff going on. As always, it was fun to talk about the dragon...

January 23, 2017. Aasa and I attended the yearly celebration of Villum Kann Rasmussen (click for rare pictures of me wearing a tie)

December 21, 2016. The Villum Foundation has awarded me a Young Investigator grant. Absolutely amazing, and very humbling! As a consequence, I have several open positions at both PhD and post doc levels.

December 12, 2016. Returned from NIPS to find a big NVIDIA GPU on my desk. Thanks to the NVIDIA crowd for this delightful gift!

December 6, 2016. Georgios and I presented the LAND paper at NIPS. Huge crowd of fun and interesting researchers!

November 16, 2016. Finally got around to putting the camera-ready version of our NIPS paper on locally adaptive normal distributions online. You can also check out the spotlight video.

August 23, 2016. Had fun lecturing about metric learning at the Advanced Topics in ML summer school. Always fun when the audience almost cries out for a Riemannian approach...

August 12, 2016. Our work on locally adaptive normal distributions has been accepted for NIPS 2016. This is a wonderfully simple way to build well-behaved nonparametric models. I'll link to the camera-ready version when it's finished.

June 26, 2016. Presented our Open Problems paper at COLT. Many interesting discussions followed -- clearly COLT is a very curious community.

June 26, 2016. GIMLI is over. We had an amazing set of speakers, but equally important we also had an amazing set of attendees. Great discussions!

June 16, 2016. It seems I was given an Outstanding Reviewer Award from the ICML 2016 program committee -- thanks!

June 15, 2016. As promised, a preprint is now available for the recent NeuroImage paper. The final version is available from Elsevier.

June 10, 2016. Sofie, myself, and Lars get our work on modeling forward models for EEG source reconstruction accepted at NeuroImage. Sometimes I'm amazed at how far you can get just using PCA... I'll link to the paper as soon as possible.

June 9, 2016. Georgios, Lars and I finally put our work on locally adaptive normal distributions online. This is a really cool example of how Riemannian geometry is useful for nonparametrics!

May 23, 2016. Aasa and I have an "Open Problems" paper at this years COLT posing problems around the probability of seeing a positive definite kernel matrix over geodesic spaces. Quite an intriguing problem; do think about it :-)

May 10, 2016. Politken, the largest Danish newspaper, is running a story about our augmentation paper. Check it out (in Danish).

May 9, 2016. Talked about the augmentation paper at AISTATS. Was great to show of the dragon :-)

May 2, 2016. I finally put the final version of the augmentation paper online. This really is a fun example of how diffeomorphisms can be of great use in machine learning. Hope to see you for the talk at AISTATS!

April 19, 2016. Oren, Michael and I are organizing an ICML workshop on the role of geometry in machine learning. Do submit an abstract!

March 23, 2016. Oren finalized the first draft of the journal version of the diffeomorphisms we published at ICCV. A preprint is now online. Code is also available.

February 5, 2016. I use Sozi (the extension) together with Inkscape for creating slides. Sometimes it can be helpful to have a PDF version of the slides rather than viewing the SVG file in your browser. I've hacked together a naive script for making this conversion -- it may be helpful to you as well.

January 12, 2016. The PAMI version of the Grassmann Average paper is now online. More theory, more experiments, more pictures. Fun stuff!

December 28, 2015. Our paper on learning data augmentation schemes has been accepted at AISTATS. If you just can't wait for the talk, you can enjoy the arXiv version, which essentially match the submitted paper. I'll link to the camera-ready once it's done.

December 28, 2015. I've added some errata (1, 2, 3, 4) to a few papers. These are merely typos, but it's good to document them when you find them -- let me know if you find more!

November 9, 2015. My PAMI paper on generalizing the classic principal curves to Riemannian manifolds is now online. It's remarkable how well such a simple well-known algorithm works compared to standard Riemannian models.

October 13, 2015. Our paper on learning data augmentation schemes is now available online. This is a great example of why everybody should care about diffeomorphisms!

October 7, 2015. Aasa and I presented the MICCAI paper on probabilistic shortest path tractography. Was great fun to put the random geometries out there!

October 6, 2015. Philipp, Marcel, and I gave a fun tutorial on Gaussian Processes at MICCAI 2015. I had the pleasure of giving people a first taste of probabilistic numerics -- yummy!

September 18, 2015. Our ICCV 2015 paper on simple and efficient representations of diffeomorphisms is now online. I'm very excited that diffeomorphisms can be so simple to work with -- this is really a big change compared to standard representations!

June 28, 2015. Uploaded the SIMBAD abstract, which basically summarizes the CVPR 2015 kernel paper. If you're in Copenhagen in October, do join Aasa's poster :-)

June 17, 2015. I'll be on paternity leave until January 2016, so my response time might be suboptimal in the mean time. If you really want a reply from me, and you don't get one, just keep trying :-)

June 9, 2015. Presented the Geodesic Exponential Kernels paper at CVPR with Aasa and François. Amazing to see such a large audience for a paper with mostly negative results.

May 28, 2015. Seems like I got an Outstanding Reviewer Award from the CVPR organizers -- thanks!

May 26, 2015. The paper presentation video for our MICCAI 2015 paper is now on Youtube -- hope you enjoy my sketchy drawings!

May 20, 2015. Our MICCAI 2015 paper on random Riemannian geometry in tractography is now online. We seem to be able to do more and more with the random geometries -- fun times!

April 21, 2015. Presented some of the tractography work at the Probabilistic Numerics for Differential Equations workshop at Warwick -- very entertaining interactions on the role of uncertainty in computations.

April 13, 2015. Our paper on geodesic exponential kernels has been accepted at CVPR 2015. Check out the paper or the extended abstract.

April 13, 2015. We're currently on our way back from DALI 2015; An extremely exciting small-scale meeting consisting of nothing but awesome talks and discussions.

November 4, 2014. Did you ever feel like designing a Gaussian kernel on a Riemannian manifold using the intrinsic metric? Or perhaps on a more general metric space? If so, you will want to tread lightly as this is generally not possible; check out our recent work on this if you're curious!

October 3, 2014. I just noticed that my Youtube channel has gotten more than one thousand views. Wow -- thanks for watching!

September 24, 2014. Gave a talk about Random Riemannian metrics in John's SLI group at MIT -- I absolutely love it when discussions outweigh presentations (fantastic crowd of people!)

September 23, 2014. Gave a Vision seminar at MIT about Grassmann averages -- a wonderfully sharp and interactive audience (and great food!)

September 17, 2014. Michael and Niklas presented our poster at MICCAI 2014 on using probabilistic numerics in tractography. There was a rather large interest in understanding the hidden uncertainties in the numerical algorithms we tend to take for granted -- wonderful!

September 12, 2014. Gave a talk on Grassmann Averages work at the Dept. of Biomedical Engineering at the City College of New York. Impressive work going on at Lucas's lab.

September 10, 2014. Presented the Grassmann Average work at the Columbia Statistics Department. I really love giving talks in front of such an intelligent and interactive crowd.

August 28, 2014. Lectured the morning session of the Advanced Topics in Machine Learning summer school at DTU -- a rather fun interactive coding session on Geometric Statistics.

August 21, 2014. Attended the Roundtable on Probabilistic Numerics in Tubingen -- it seems the community is beginning to form!

August 7, 2014. The poster teaser video for our MICCAI 2014 paper is now online -- check it out!

August 7, 2014. My talk at CVPR 2014 on Grassmann Averages is now available at techtalks.tv -- enjoy!

July 2, 2014. Posted a blog entry about choices of subspace metrics for the Grassmann Average subspace estimator. Summary: for Gaussian data most metrics gives the first principal component as the subspace average.

June 27, 2014. Presented the paper Grassmann Averages for Scalable PCA at CVPR 2014. I'll link to the talk recording once it goes live.

June 24, 2014. Presented the poster for Model Transport: Towards Scalable Transfer Learning on manifolds with Michael at CVPR 2014. Much fun!

May 30, 2014. The paper Metrics for Probabilistic Geometries has been accepted at UAI 2014. It's all about distributions of manifolds in the form of random Riemannian metrics -- very exciting first steps!

April 14, 2014. The paper Probabilistic shortest path tractography in DTI using Gaussian Process ODE solvers has been accepted at MICCAI 2014. This is a cool case-study for probabilistic numerics.