Leena C Vankadara
@leenaCvankadara
Followers
277
Following
221
Media
0
Statuses
45
Lecturer (Assistant Professor) @GatsbyUCL; Applied Scientist II @Amazon Research; Previously @uni_tue and @MPI_IS; https://t.co/4kC5e6oStF
Tuebingen, Germany
Joined October 2009
Research Fellow position open at @GatsbyUCL to work with me and @jasonhartford on Causality in Biological Systems! Apply at link, deadline is 27 August: https://t.co/QYkd4trSA6
ucl.ac.uk
UCL is consistently ranked as one of the top ten universities in the world (QS World University Rankings 2010-2022) and is No.2 in the UK for research power (Research Excellence Framework 2021).
0
17
74
π’ Job alert We are looking for a Postdoctoral Fellow to work with @ArthurGretton on creating statistically efficient causal and interaction models with the aim of elucidating cellular interactions. β°Deadline 27-Aug-2025 βΉοΈ
ucl.ac.uk
UCL is consistently ranked as one of the top ten universities in the world (QS World University Rankings 2010-2022) and is No.2 in the UK for research power (Research Excellence Framework 2021).
2
5
30
π’ We have an opportunity for students to join our PhD programme in Theoretical Neuroscience and Machine Learning this September. Application deadline is 27 May 2025. Information & how to apply π
ucl.ac.uk
Students study toward a PhD in machine learning or computational/theoretical neuroscience, with minor emphasis in the complementary field.
0
57
141
Weβre looking for interns at the Palmigiano Lab in the Gatsby Unit! https://t.co/E0OUnwh2RP. These are 3-month, paid internships focused on theoretical and CS-based neuroscience projects. Apply through the Gatsby website: https://t.co/xKcJWQUrfA. Deadline Jan 17!
ucl.ac.uk
Join us and be part of a vibrant community of research and innovation.
0
16
48
π’ Apply now for the 7-week #Mathematics #SummerSchool in London! You will develop mathematics skills and intuition necessary to enter the #TheoreticalNeuroscience or #MachineLearning field. βΉοΈ https://t.co/DJXiD3lbc6 Please help spread the word!
1
52
136
Welcome to our fine-tuning workshop #NeurIPS2024 at Saturday East Exhibition Hall A! Many thanks for @Azaliamirh @jasondeanlee @tydsh @QuanquanGu @danqi_chen @tri_dao Anna @btreetaiji @leenaCvankadara support!
4
10
39
Application deadline for the Gatsby PhD program on Monday 11th November! Fully funded for students of all nationalities.
β° Deadline Monday 11 November π Apply now to join this amazing community! Gatsby Unit: https://t.co/bvWbj7swV1 SWC: https://t.co/idNmv5kJHo Joint:
1
7
25
Exciting moment for ML!
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton βfor foundational discoveries and inventions that enable machine learning with artificial neural networks.β
0
0
3
Applying to the #ELLISPhD Program? If you are selecting a Gatsby Unit faculty member as your main supervisor, please don't forget to apply to the Gatsby Unit PhD Programme in parallel. Our deadline is 11 November 2024. π
ucl.ac.uk
Students study toward a PhD in machine learning or computational/theoretical neuroscience, with minor emphasis in the complementary field.
The #ELLISPhD application portal is now open! Apply to top #AI labs & supervisors in Europe with a single application, and choose from different areas & tracks. The call for applications: https://t.co/og6xzr14tj Deadline: 15 November 2024 #PhD #PhDProgram #MachineLearning #ML
0
3
7
I am thrilled to announce that I will be joining the Gatsby Computational Neuroscience Unit at UCL as a Lecturer (Assistant Professor) in Feb 2025! Looking forward to working with the exceptional talent at @GatsbyUCL on cutting-edge problems in deep learning and causality.
We are delighted to announce that Dr Leena Chennuru Vankadara will join the Unit as Lecturer in Feb 2025, developing theoretical understandings of scaling and generalization in deep learning and causality. Welcome aboard @leenaCvankadara! Learn more at https://t.co/jASvmzGZFP
10
6
66
π’ Applications for 2025 Gatsby Unit PhD programme are open! Submit by 11 Nov 2024. π° Fully funded regardless of nationality βΉοΈ https://t.co/bvWbj7rZ5t
1
55
125
1/n Introducing SOAP (ShampoO with Adam in the Preconditioner's eigenbasis): A deep learning optimization algorithm that applies Adam in Shampoo's eigenbasis. SOAP outperforms both AdamW and Shampoo in language model pretraining.
6
63
347
π¨ A postdoc position in rational machine learning in our group @CISPA. If you want to collaborate with us to create more rational, efficient, and reliable machine learning systems, don't hesitate to reach out. π https://t.co/nI6UuG2Xgu RT Appreciated π
1
29
60
Have you ever done a dense grid search over neural network hyperparameters? Like a *really dense* grid search? It looks like this (!!). Blueish colors correspond to hyperparameters for which training converges, redish colors to hyperparameters for which training diverges.
272
2K
10K
Consider submission to our ICML 2021 workshop: Overparameterization: Pitfalls & Opportunities https://t.co/bH1hgAq1Xj focused specifically on the role of overparameterization in machine learning. Organized by @HanieSedghi @QuanquanGu @aminkarbasi & myself. Deadline: June 21
sites.google.com
Overview Modern machine learning models are often highly overparameterized. The prime examples of late are neural network architectures that can achieve state-of-the-art performance while having many...
1
34
138
As I struggled to deal with the impact of COVID on my family members in India, I got delayed by a day for submitting my reviews for a conference & I got a message from a senior reviewer with the blurb below. My humble request to everyone - pls don't say this to anyone ever! [1/n]
1K
5K
34K
The whole piece is insightful and eye-opening, but this particular quote, I believe, is crucial. https://t.co/xtQzPJOiS1
2
5
53
Another set of great talks @IMSI_Institute today by Samory Kpotufe, @arkrause, and @kamalikac! https://t.co/nmAydn63gP
0
5
17
AISTATS oral by my students/collaborators Leena Vankadara, Sebastian Bordt, Debarghya Ghoshdastidar (April 13, 10:30 am PDT): Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models. https://t.co/Igze5Aw3MH
https://t.co/tuPyAQ0Gnc
@leena_suresh
0
3
22
I am beginning to read JMLR paper by Halbert White and Karim Chalak on limitations of DAGs/SCMs in dealing optimization, equilibrium, learning, which are of "central interest to economists and econometricians". Comments/suggestions/joint reading is welcome. @yudapearl
2
22
136