Ankit Singh Rawat

Samet Oymak

CoRR, 2024

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers.

[BibT_eX]

[DOI]

Muhammed Emrullah Ildiz

CoRR, 2024

2023

DistillSpec: Improving Speculative Decoding via Knowledge Distillation.

[BibT_eX]

[DOI]

CoRR, 2023

What do larger image classifiers memorise?

[BibT_eX]

[DOI]

CoRR, 2023

Think before you speak: Training Language Models With Pause Tokens.

[BibT_eX]

[DOI]

CoRR, 2023

EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval.

[BibT_eX]

[DOI]

Veeranjaneyulu Sadhanala

CoRR, 2023

ResMem: Learn what you can and memorize the rest.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

When Does Confidence-Based Cascade Deferral Suffice?

[BibT_eX]

[DOI]

Wittawat Jitkrittum

Neha Gupta

Aditya Krishna Menon

Harikrishna Narasimhan

Sanjiv Kumar

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On the Role of Attention in Prompt-tuning.

[BibT_eX]

[DOI]

Samet Oymak

Mahdi Soltanolkotabi

Proceedings of the International Conference on Machine Learning, 2023

A Statistical Perspective on Retrieval-Based Models.

[BibT_eX]

[DOI]

Soumya Basu

Manzil Zaheer

Proceedings of the International Conference on Machine Learning, 2023

Teacher Guided Training: An Efficient Framework for Knowledge Transfer.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Serving Graph Compression for Graph Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Supervision Complexity and its Role in Knowledge Distillation.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Large Language Models with Controllable Working Memory.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022

Large Language Models with Controllable Working Memory.

[BibT_eX]

[DOI]

CoRR, 2022

Large Models are Parsimonious Learners: Activation Sparsity in Trained Transformers.

[BibT_eX]

[DOI]

CoRR, 2022

Generalization Properties of Retrieval-based Models.

[BibT_eX]

[DOI]

Soumya Basu

Manzil Zaheer

CoRR, 2022

ELM: Embedding and Logit Margins for Long-Tail Learning.

[BibT_eX]

[DOI]

CoRR, 2022

FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients.

[BibT_eX]

[DOI]

CoRR, 2022

A Fourier Approach to Mixture Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Post-hoc estimators for learning to defer to an expert.

[BibT_eX]

[DOI]

Harikrishna Narasimhan

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

In defense of dual-encoders for neural ranking.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

2021

When in Doubt, Summon the Titans: Efficient Inference with Large Models.

[BibT_eX]

[DOI]

CoRR, 2021

Distilling Double Descent.

[BibT_eX]

[DOI]

Andrew Cotter

Aditya Krishna Menon

Harikrishna Narasimhan

Sashank J. Reddi

Yichen Zhou

CoRR, 2021

On the Reproducibility of Neural Network Predictions.

[BibT_eX]

[DOI]

CoRR, 2021

Byzantine Resilient Distributed Clustering with Redundant Data Assignment.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2021

Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

A statistical perspective on distillation.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Overparameterisation and worst-case generalisation: friend or foe?

[BibT_eX]

[DOI]

Aditya Krishna Menon

Sanjiv Kumar

Proceedings of the 9th International Conference on Learning Representations, 2021

Long-tail learning via logit adjustment.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

RankDistil: Knowledge Distillation for Ranking.

[BibT_eX]

[DOI]

Sashank J. Reddi

Rama Kumar Pasumarthi

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

The Generalized Lasso for Sub-Gaussian Measurements With Dithered Quantization.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2020

Modifying Memories in Transformer Models.

[BibT_eX]

[DOI]

CoRR, 2020

Why distillation helps: a statistical perspective.

[BibT_eX]

[DOI]

CoRR, 2020

Doubly-stochastic mining for heterogeneous retrieval.

[BibT_eX]

[DOI]

CoRR, 2020

O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Adversarial robustness via robust low rank representations.

[BibT_eX]

[DOI]

Pranjal Awasthi

Himanshu Jain

Aravindan Vijayaraghavan

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Robust large-margin learning in hyperbolic space.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Reliable Distributed Clustering with Redundant Data Assignment.

[BibT_eX]

[DOI]

Venkata Gandikota

Proceedings of the IEEE International Symposium on Information Theory, 2020

Federated Learning with Only Positive Labels.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Low-Rank Bottleneck in Multi-head Attention Models.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Are Transformers universal approximators of sequence-to-sequence functions?

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Can gradient clipping mitigate label noise?

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Achieving Multi-port Memory Performance on Single-Port Memory with Coding Techniques.

[BibT_eX]

[DOI]

Proceedings of the 3rd International Conference on Information and Computer Technologies, 2020

2019

Sampled Softmax with Random Fourier Features.

[BibT_eX]

[DOI]

Jiecao Chen

Felix X. Yu

Ananda Theertha Suresh

Sanjiv Kumar

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Robust Gradient Descent via Moment Encoding and LDPC Codes.

[BibT_eX]

[DOI]

Raj Kumar Maity

Proceedings of the IEEE International Symposium on Information Theory, 2019

Robust Direction of Arrival Estimation in the Presence of Array Faults using Snapshot Diversity.

[BibT_eX]

[DOI]

Gary C. F. Lee

Gregory W. Wornell

Proceedings of the 2019 IEEE Global Conference on Signal and Information Processing, 2019

Learning and Recovery in the ReLU Model.

[BibT_eX]

[DOI]

Proceedings of the 57th Annual Allerton Conference on Communication, 2019

Lifting high-dimensional non-linear models with Gaussian regressors.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

MDS Code Constructions With Small Sub-Packetization and Near-Optimal Repair Bandwidth.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2018

Centralized Repair of Multiple Node Failures With Applications to Communication Efficient Secret Sharing.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2018

Robust Gradient Descent via Moment Encoding with LDPC Codes.

[BibT_eX]

[DOI]

Raj Kumar Maity

CoRR, 2018

Representation Learning and Recovery in the ReLU Model.

[BibT_eX]

[DOI]

CoRR, 2018

The Generalized Lasso for Sub-gaussian Observations with Dithered Quantization.

[BibT_eX]

[DOI]

Proceedings of the 56th Annual Allerton Conference on Communication, 2018

2017

MDS Code Constructions with Small Sub-packetization and Near-optimal Repair Bandwidth.

[BibT_eX]

[DOI]

Venkatesan Guruswami

Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete Algorithms, 2017

∊-MSR codes with small sub-packetization.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017

Secrecy capacity of minimum storage regenerating codes.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017

Efficient data access in hybrid cloud storage.

[BibT_eX]

[DOI]

Islam Samy

Proceedings of the 55th Annual Allerton Conference on Communication, 2017

Associative Memory Using Dictionary Learning and Expander Decoding.

[BibT_eX]

[DOI]

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

2016

Locality and Availability in Distributed Storage.

[BibT_eX]

[DOI]

Dimitris S. Papailiopoulos

IEEE Trans. Inf. Theory, 2016

A Note on Secure Minimum Storage Regenerating Codes.

[BibT_eX]

[DOI]

CoRR, 2016

New MDS codes with small sub-packetization and near-optimal repair bandwidth.

[BibT_eX]

[DOI]

Venkatesan Guruswami

CoRR, 2016

Progress on high-rate MSR codes: Enabling arbitrary number of helper nodes.

[BibT_eX]

[DOI]

Proceedings of the 2016 Information Theory and Applications Workshop, 2016

Centralized repair of multiple node failures.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2016

Distance preserving maps and combinatorial joint source-channel coding for large alphabets.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2016

2015

Error-Correcting Regenerating and Locally Repairable Codes via Rank-Metric Codes.

[BibT_eX]

[DOI]

Natalia Silberstein

IEEE Trans. Inf. Theory, 2015

Cooperative local repair in distributed storage.

[BibT_eX]

[DOI]

EURASIP J. Adv. Signal Process., 2015

Associative Memory via a Sparse Recovery Model.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

On adversarial joint source channel coding.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2015

Understanding contention-based channels and using them for defense.

[BibT_eX]

[DOI]

Casen Hunger

Mikhail Kazdagli

Mohit Tiwari

Proceedings of the 21st IEEE International Symposium on High Performance Computer Architecture, 2015

2014

Secure Cooperative Regenerating Codes for Distributed Storage Systems.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2014

Batch Codes through Dense Graphs without Short Cycles.

[BibT_eX]

[DOI]

Anna Gál

Zhao Song

Electron. Colloquium Comput. Complex., 2014

Dynamic control of video quality for AVS.

[BibT_eX]

[DOI]

Emina Soljanin

Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014

Secure distributed storage systems: Local repair with minimum bandwidth regeneration.

[BibT_eX]

[DOI]

Proceedings of the 6th International Symposium on Communications, 2014

On codes with availability for distributed storage.

[BibT_eX]

[DOI]

Dimitris S. Papailiopoulos

Proceedings of the 6th International Symposium on Communications, 2014

2013

Scheduling Algorithms for MU-MIMO with Partial Current CSIT and Full Delayed CSIT.

[BibT_eX]

[DOI]

Haralabos C. Papadopoulos

Ozgun Y. Bursalioglu

Proceedings of the 77th IEEE Vehicular Technology Conference, 2013

Optimal locally repairable codes with local minimum storage regeneration via rank-metric codes.

[BibT_eX]

[DOI]

Proceedings of the 2013 Information Theory and Applications Workshop, 2013

Optimal locally repairable codes via rank-metric codes.

[BibT_eX]

[DOI]

Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013

Secure locally repairable codes for distributed storage systems.

[BibT_eX]

[DOI]

Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013

The secrecy capacity of minimum bandwidth cooperative regenerating codes.

[BibT_eX]

[DOI]

Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013

Explicit MBR all-symbol locality codes.

[BibT_eX]

[DOI]

Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013

Availability and locality in distributed storage.

[BibT_eX]

[DOI]

Dimitris S. Papailiopoulos

Proceedings of the IEEE Global Conference on Signal and Information Processing, 2013

Learning the causal graph of Markov time series.

[BibT_eX]

[DOI]

Proceedings of the 51st Annual Allerton Conference on Communication, 2013

2012

Optimal Locally Repairable and Secure Codes for Distributed Storage Systems

[BibT_eX]

[DOI]

CoRR, 2012

Adversarial Error Resilience in Distributed Storage Using MRD Codes and MDS Array Codes

[BibT_eX]

[DOI]

Natalia Silberstein

CoRR, 2012

On locality in distributed storage systems.

[BibT_eX]

[DOI]

Proceedings of the 2012 IEEE Information Theory Workshop, 2012

Error resilience in distributed storage via rank-metric codes.

[BibT_eX]

[DOI]

Natalia Silberstein