Ekdeep Singh Lubana

Orcid: 0000-0002-7200-9341

According to our database1, Ekdeep Singh Lubana authored at least 23 papers between 2018 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model.
CoRR, 2024

2023
FoMo Rewards: Can we cast foundation models as reward functions?
CoRR, 2023

How Capable Can a Transformer Become? A Study on Synthetic, Interpretable Tasks.
CoRR, 2023

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks.
CoRR, 2023

In-Context Learning Dynamics with Random Binary Sequences.
CoRR, 2023

Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Mechanistic Mode Connectivity.
Proceedings of the International Conference on Machine Learning, 2023

What shapes the loss landscape of self supervised learning?
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
Analyzing Data-Centric Properties for Contrastive Learning on Graphs.
CoRR, 2022

Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices.
Proceedings of the WWW '22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25, 2022

Analyzing Data-Centric Properties for Graph Contrastive Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering.
Proceedings of the International Conference on Machine Learning, 2022

How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation.
Proceedings of the Conference on Lifelong Learning Agents, 2022

2021
Beyond BatchNorm: Towards a General Understanding of Normalization in Deep Learning.
CoRR, 2021

Rethinking Quadratic Regularizers: Explicit Movement Regularization for Continual Learning.
CoRR, 2021

Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

A Gradient Flow Framework For Analyzing Network Pruning.
Proceedings of the 9th International Conference on Learning Representations, 2021

2020
OrthoReg: Robust Network Pruning Using Orthonormality Regularization.
CoRR, 2020

Intelligent Scene Caching to Improve Accuracy for Energy-Constrained Embedded Vision.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
Minimalistic Image Signal Processing for Deep Learning Applications.
Proceedings of the 2019 IEEE International Conference on Image Processing, 2019

Machine Foveation: An Application-Aware Compressive Sensing Framework.
Proceedings of the Data Compression Conference, 2019

2018
Digital Foveation: An Energy-Aware Machine Vision Framework.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., 2018

Snap: Chlorophyll Concentration Calculator Using RAW Images of Leaves.
Proceedings of the 2018 IEEE SENSORS, New Delhi, India, October 28-31, 2018, 2018


  Loading...