You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
abstract = {The Lottery Ticket Hypothesis continues to have a profound practical impact on the quest for small scale deep neural networks that solve modern deep learning tasks at competitive performance. These lottery tickets are identified by pruning large randomly initialized neural networks with architectures that are as diverse as their applications. Yet, theoretical insights that attest their existence have been mostly focused on deed fully-connected feed forward networks with ReLU activation functions. We prove that also modern architectures consisting of convolutional and residual layers that can be equipped with almost arbitrary activation functions can contain lottery tickets with high probability.},
abstract={Open access to software in computational and systems biology, including data, code and models, is widely acknowledged as essential for ensuring reproducibility of research results and reuse of methods1. Although there are software tools that allow sharing of computational pipelines, these systems generally do not allow the integration of software annotation and documentation at each step in the process — elements that are required to understand and run complex and rapidly evolving software, including methods developed in systems biology for inferring biological pathways. Our research team has been developing network inference and analysis methods, collected into the Network Zoo (http://netzoo.github.io), with implementations in R, C, MATLAB and Python. The growing community of users of these network resources, the increasing interest in learning how to apply network inference methods, and the need to ensure that published analyses are fully reproducible led us to develop Netbooks (http://netbooks.networkmedicine.org), a hosted collection of Jupyter notebooks that provide detailed and annotated step-by-step case studies of GRN analysis.},
280
-
img={nature-methods.jpg}
281
-
}
282
-
283
-
@misc{fischer2022lotteryticketsnonzerobiases,
284
-
title={Lottery Tickets with Nonzero Biases},
285
-
author={Jonas Fischer and Advait Gadhikar and Rebekka Burkholz},
Copy file name to clipboardExpand all lines: _data/alumni_members.yml
+3Lines changed: 3 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -7,13 +7,15 @@
7
7
end_date: Oct 24
8
8
email: adarsh.jamadandi@cispa.de
9
9
url: https://adarshmj.github.io
10
+
next: PhD at IRISA, Université de Rennes
10
11
11
12
- name: Harsha Nelaturu
12
13
last_name: Nelaturu
13
14
photo: c02hane.jpg
14
15
start_date: Aug 23
15
16
end_date: Jul 24
16
17
url: https://nelaturuharsha.github.io/
18
+
next: [Applied Scientist Intern Amazon, PhD at Calgary University]
17
19
18
20
- role: Research engineers
19
21
members:
@@ -25,6 +27,7 @@
25
27
email: mikita.vedzeneyeu@cispa.de
26
28
url: https://github.com/nikitaved
27
29
description: "I am interesting in making modern AI models efficient. In particular, I work on discovering and exploiting structure in Neural Networks (sparsity, low-dimensional representations and similar) for efficient training, fine-tuning and inference. I am a former full-time core developer for [PyTorch](https://github.com/pytorch/pytorch) and [Lightning Thunder](https://github.com/Lightning-AI/lightning-thunder). Check my [GitHub](https://github.com/nikitaved) to see what I work on now."
Copy file name to clipboardExpand all lines: _data/news.yml
+13-4Lines changed: 13 additions & 4 deletions
Original file line number
Diff line number
Diff line change
@@ -1,9 +1,15 @@
1
+
- date: 12. June 2025
2
+
headline: "Tom is attending the [AIM](https://aimath.nl/index.php/2025/03/13/4th-aim-cluster-event-tilburg/) (AI & Mathematics) workshop at Tilburg University."
3
+
1
4
- date: 2. June 2025
2
-
headline: "Rebekka and Celia are presenting at [NetSci](https://netsci2025.github.io/) in Maastricht with a satellite keynote and a lightning talk."
5
+
headline: "Rebekka and Celia are presenting at [NetSci](https://netsci2025.github.io/) in Maastricht with a [satellite keynote](/outreach#netbiomed-2025-keynote-jun-2-2025) and a lightning talk."
3
6
4
7
- date: 1. June 2025
5
8
headline: "Welcome Baraah!"
6
9
10
+
- date: 27. May 2025
11
+
headline: "Celia is visiting TU Wien and presenting at the ML Research Unit's [seminar](https://ml-tuw.github.io/ruml_seminar/)."
12
+
7
13
- date: 7. May 2025
8
14
headline: "Congratulations to Rebekka for [receiving tenure](https://cispa.de/en/burkholz-tenured) at CISPA."
9
15
@@ -14,7 +20,7 @@
14
20
headline: "Rebekka is at [CPAL](https://cpal.cc/spotlight_track/) presenting three [papers](/publications) as recent spotlights."
15
21
16
22
- date: 13. February 2025
17
-
headline: "Celia is presenting her work on graph rewiring at Cohere Labs ([watch talk here](/outreach/#celia-rubio-madrigal--cohere-labs-feb-13-2025))."
23
+
headline: "Celia is presenting her work on graph rewiring at Cohere Labs ([video](/outreach#celia-rubio-madrigal--cohere-labs-feb-13-2025))."
18
24
19
25
- date: 22. January 2025
20
26
headline: "Two papers
@@ -25,18 +31,21 @@
25
31
- date: 1. December 2024
26
32
headline: "Welcome to Gowtham and Nik!"
27
33
34
+
- date: 25. December 2024
35
+
headline: "Celia, Adarsh, Rebekka, and Nimrah are presenting their work at the [ELLIS Pre-NeurIPS](https://lacoco-lab.github.io/events/PreNeurIPS2024/) Session in Saarbrücken."
36
+
28
37
- date: 25. September 2024
29
38
headline: "Three papers
30
39
[(1)](https://openreview.net/forum?id=EMkrwJY2de)
31
40
[(2)](https://openreview.net/forum?id=IfZwSRpqHl)
32
41
[(3)](https://openreview.net/forum?id=FNtsZLwkGr)
33
-
have been accepted at NeurIPS 2024."
42
+
have been accepted at NeurIPS 2024, and [one](https://sites.google.com/wimlworkshop.org/wiml-2024/program) at the WiML Workshop, where Rebekka is an invited mentor."
34
43
35
44
- date: 1. July 2024
36
45
headline: "Welcome to Chao, Rahul, and Dong!"
37
46
38
47
- date: 14. June 2024
39
-
headline: "Celia, Advait and Adarsh are presenting at the Helmholtz AI Conference: AI for Science ([HAICON](https://eventclass.it/haic2024/scientific/external-program/session?s=S-05a)) in Düsseldorf ([watch talk here](/outreach/#celia-rubio-madrigal--haicon-jun-14-2024))."
48
+
headline: "Celia, Advait, and Adarsh are presenting at the Helmholtz AI Conference: AI for Science ([HAICON](https://eventclass.it/haic2024/scientific/external-program/session?s=S-05a)) in Düsseldorf ([video](/outreach#celia-rubio-madrigal--haicon-jun-14-2024))."
40
49
41
50
- date: 1. May 2024
42
51
headline: "Our paper on [improving GATs](https://openreview.net/forum?id=Sjv5RcqfuH) has been accepted at ICML 2024."
abstract: "Deep learning continues to achieve impressive breakthroughs across disciplines but relies on increasingly large neural network models that are trained on massive data sets. Their development inflicts costs that are only affordable by a few labs and prevent global participation in the creation of related technologies. In this talk, we will ask the question if it really has to be like this and discuss some of the major challenges that limit the success of deep learning on smaller scales. We will give three examples of complimentary approaches that could help us address the underlying issues: (i) early neural network sparsification, (ii) the integration of useful inductive bias in the design of problem specific neural network architectures (with biomedical applications), and (iii) the improvement of training from scratch in the context of graph neural networks."
50
49
51
50
- title: "Pruning Deep Neural Networks for Lottery Tickets"
- title: "Artificial Intelligence in Echocardiography Diagnostics – Detection of Takotsubo Syndrome"
80
+
authors: "D Di Vece, F Laumer, M Schwyzer, R Burkholz, L Corinzia, V.L Cammann, R Citro, J Bax, J.R Ghadri, J.M Buhmann, C Templin"
81
+
conference: European Heart Journal, Volume 41, 2020
82
+
link: https://doi.org/10.1093/ehjci/ehaa946.1221
83
+
noiframe: true
81
84
82
85
podcasts:
83
86
- title: "Demokratie statt Datenmonopol"
@@ -117,4 +120,15 @@ podcasts:
117
120
venue: "CISPA TL;DR"
118
121
description: "CISPA-Faculty Dr. Rebekka Burkholz spricht in dieser Folge mit uns darüber, was relationales maschinelles Lernen ist und welche Chancen Methoden des maschinellen Lernens in der Diagnostik und Behandlung von Krankheiten eröffnen. Die Mathematikerin gibt zudem Einblicke, was Informatiker:innen und Mathematiker:innen unterscheidet und was aus ihrer Sicht helfen würde, mehr Frauen für eine Karriere in der Forschung zu begeistern."
description: "After coffee break we had Rebekka Burkholz discussing current challenges when modelling gene regulation and how to fix them. Her approach is innovative and allows us to infer biological processes with both scalability and interpretability."
description: "Beim Berlin Summer Meeting am MDC-BIMSB trafen sich Molekularbiolog\\*innen und Bioinformatiker\\*innen, um die neuesten Erfolge und Herausforderungen zu diskutieren. Sie loteten aus, wie sie Künstliche Intelligenz am besten für die Biomedizin nutzen können."
description: "I lead the Relational Machine Learning Group at the Helmholtz Center CISPA since 2021. Our research on sparse deep learning is funded by an [ERC starting grant](https://cispa.de/en/research/grants/sparse-ml) since December 2023 and by Apple Research since August 2025. From 2019-2021, I was a PostDoc at the Biostatistics Department of the Harvard T.H. Chan School of Public Health working with John Quackenbush, from 2017-2018 at the Institute for Machine Learning at ETH Zurichwith Joachim Buhmann, and from 2016-2017 at the Chair of Systems Design at ETH Zurich with Frank Schweitzer. My PhD research at the ETH Risk Center was supervised by Frank Schweitzer and co-supervised by Hans J. Herrmann from 2013-2016. My thesis on systemic risk won the Zurich Dissertation Prize and our work on international maize trade received the CSF Best Contribution Award. I studied Mathematics and Physics at TU Darmstadt."
description: "I focus on understanding the intricate dynamics of training and fine-tuning in machine learning models, with the goal of developing more efficient and effective learning algorithms. My research explores how optimization processes evolve and how we can refine these methods to improve performance. Currently, I am particularly interested in gradient compression techniques."
description: "I work on research problems at the intersection of machine learning and causality, focusing on modeling, inference, and interpreting machine learning models from a causal perspective to enhance their robustness and trustworthiness."
description: "I work on building provable algorithms for deep learning and am currently interested in algorithms related to sparsity in neural nets. Specifically I am interested in the Lottery Ticket Hypothesis and how it can help identify the underlying structure of a learnt network."
description: "My research addresses generalization challenges in graph learning, focusing on the dual role of input graphs as both data and computation structures, and the effects of modifying them under different criteria. I hold two degrees in Mathematics and Computer Science from Universidad Complutense de Madrid, and I received the prestigious postgraduate fellowship from la Caixa Foundation in 2022. This allowed me to study a master's at Strathclyde in the UK, where I was awarded the Best Overall Performance Prize."
description: "My research interests lie at the intersection of understanding neural network training dynamics and designing efficient deep learning methods. Concretely, I work with theoretical tools such as mirror flow, regularization techniques, and mean field descriptions to study the effect of overparameterization and improve model efficiency."
<p>We are part of the <ahref="https://cispa.de">CISPA Helmholtz Center for Information Security</a>, at the <ahref="https://www.uni-saarland.de">Saarland University</a>campus.</p>
7
+
<p>We are part of the <ahref="https://cispa.de">CISPA Helmholtz Center for Information Security</a> in Saarbrücken and St. Ingbert, Germany, and are grateful to <ahref="https://www.uni-saarland.de">Saarland University (UdS)</a> for granting us supervision rights.</p>
0 commit comments