Nandan Kumar Jha

According to our database, Nandan Kumar Jha authored at least 25 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws.

Nandan Kumar Jha, Brandon Reagen

CoRR, May, 2026

NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks.

Nandan Kumar Jha, Brandon Reagen

CoRR, March, 2026

2025

Network and Compiler Optimizations for Efficient Linear Algebra Kernels in Private Transformer Inference.

Karthik Garimella, Negar Neda, Austin Ebel, Nandan Kumar Jha, Brandon Reagen

CoRR, December, 2025

Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?

Nandan Kumar Jha, Brandon Reagen

CoRR, October, 2025

A Random Matrix Theory Perspective on the Learning Dynamics of Multi-head Latent Attention.

Nandan Kumar Jha, Brandon Reagen

CoRR, July, 2025

Entropy-Guided Attention for Private LLMs.

Nandan Kumar Jha, Brandon Reagen

CoRR, January, 2025

Network and Compiler Optimizations for Efficient Linear Algebra Kernels in Private Transformer Inference (Invited Paper).

Karthik Garimella, Negar Neda, Austin Ebel, Nandan Kumar Jha, Brandon Reagen

Proceedings of the IEEE/ACM International Conference On Computer Aided Design, 2025

Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space?

Nandan Kumar Jha, Brandon Reagen

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

DeepReShape: Redesigning Neural Networks for Efficient Private Inference.

Nandan Kumar Jha, Brandon Reagen

Trans. Mach. Learn. Res., 2024

TruncFormer: Private LLM Inference Using Only Truncations.

Patrick Yubeaton, Jianqiao Mo, Karthik Garimella, Nandan Kumar Jha, Brandon Reagen, Chinmay Hegde, Siddharth Garg

CoRR, 2024

AERO: Softmax-Only LLMs for Efficient Private Inference.

Nandan Kumar Jha, Brandon Reagen

CoRR, 2024

ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models.

Nandan Kumar Jha, Brandon Reagen

CoRR, 2024

2023

Characterizing and Optimizing End-to-End Systems for Private Inference.

Karthik Garimella, Zahra Ghodsi, Nandan Kumar Jha, Siddharth Garg, Brandon Reagen

Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2023

2021

Modeling Data Reuse in Deep Neural Networks by Taking Data-Types into Cognizance.

Nandan Kumar Jha, Sparsh Mittal

IEEE Trans. Computers, 2021

CryptoNite: Revealing the Pitfalls of End-to-End Private Inference at Scale.

Karthik Garimella, Nandan Kumar Jha, Zahra Ghodsi, Siddharth Garg, Brandon Reagen

CoRR, 2021

Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning.

Karthik Garimella, Nandan Kumar Jha, Brandon Reagen

CoRR, 2021

Circa: Stochastic ReLUs for Private Deep Learning.

Zahra Ghodsi, Nandan Kumar Jha, Brandon Reagen, Siddharth Garg

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

DeepReDuce: ReLU Reduction for Fast Private Inference.

Nandan Kumar Jha, Zahra Ghodsi, Siddharth Garg, Brandon Reagen

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

Digital Storytelling: The Integration of Intangible and Tangible Heritage in the City of Surat, India.

Chika Udeaja, Lukman E. Mansuri, Busisiwe Chikomborero Ncube Makore, Kwasi Gyau Baffour Awuah, Dilip A. Patel, Claudia Trillo, Nandan Kumar Jha

Proceedings of the Culture and Computing. Interactive Cultural Heritage and Arts, 2021

2020

DeepPeep: Exploiting Design Ramifications to Decipher the Architecture of Compact DNNs.

Nandan Kumar Jha, Sparsh Mittal, Binod Kumar, Govardhan Mattela

ACM J. Emerg. Technol. Comput. Syst., 2020

On the Demystification of Knowledge Distillation: A Residual Network Perspective.

Nandan Kumar Jha, Rajat Saini, Sparsh Mittal

CoRR, 2020

ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks.

Rajat Saini, Nandan Kumar Jha, Bedanta Das, Sparsh Mittal, C. Krishna Mohan

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020

E2GC: Energy-efficient Group Convolution in Deep Neural Networks.

Nandan Kumar Jha, Rajat Saini, Subhrajit Nag, Sparsh Mittal

Proceedings of the 33rd International Conference on VLSI Design and 19th International Conference on Embedded Systems, 2020

DRACO: Co-Optimizing Hardware Utilization, and Performance of DNNs on Systolic Accelerator.

Nandan Kumar Jha, Shreyas Ravishankar, Sparsh Mittal, Arvind Kaushik, Dipan Mandal, Mahesh Chandra

Proceedings of the 2020 IEEE Computer Society Annual Symposium on VLSI, 2020

2019

The Ramifications of Making Deep Neural Networks Compact.

Nandan Kumar Jha, Sparsh Mittal, Govardhan Mattela

Proceedings of the 32nd International Conference on VLSI Design and 18th International Conference on Embedded Systems, 2019