Expertini Research Research

Browse Research Papers

59+ open-access research outputs.

โœ• Clear
๐Ÿ” rajiv krishnakumar
Showing 59 results for "rajiv krishnakumar"
AI & Data Science Preprint PDF DOI

Parameter Reduction Improves Vision Transformers: A Comparative Study of Sharing and Width Reduction

Anantha Padmanaban Krishna Kumar (Boston University) ยท 2025

Although scaling laws and many empirical results suggest that increasing the size of Vision Transformers often improves performance, model accuracy and training behavior are not always monotonically iโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Mechanisms of Non-Monotonic Scaling in Vision Transformers

Anantha Padmanaban Krishna Kumar (Boston University) ยท 2025

Deeper Vision Transformers often perform worse than shallower ones, which challenges common scaling assumptions. Through a systematic empirical analysis of ViT-S, ViT-B, and ViT-L on ImageNet, we idenโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels

Anantha Padmanaban Krishna Kumar (Boston University) ยท 2025

Can in-context learning (ICL) override pre-trained label semantics, or does it merely refine an existing semantic backbone? We address this question by treating LLMs as prompt-induced classifiers and โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Efficient Vector Symbolic Architectures from Histogram Recovery

Zirui Deng, Netanel Raviv ยท 2025

Vector symbolic architectures (VSAs) are a family of information representation techniques which enable composition, i.e., creating complex information structures from atomic vectors via binding and sโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Transformer-Based Decoding in Concatenated Coding Schemes Under Synchronization Errors

Julian Streit, Franziska Weindel, Reinhard Heckel ยท 2025

We consider the reconstruction of a codeword from multiple noisy copies that are independently corrupted by insertions, deletions, and substitutions. This problem arises, for example, in DNA data storโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Symbol Detection in Inter-Symbol Interference Channels using Expectation Propagation with Channel Shortening

Jannis Clausius, Luca Schmid, Laurent Schmalen, Stephan ten Brink ยท 2025

Iterative message passing detection based on expectation propagation(EP) has demonstrated near-optimum performance in many signal processing and communication scenarios. The method remains feasible evโ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

J-PAS: Discovery of RaJav, a bright spatially extended Ly$\alpha$ Nebula at z=2.25

P. T. Rahna, M. Akhlaghi, J. A. Fernandez-Ontiveros, Z. -Y. Zheng, A. Hernan-Caballero, R. Amorin, C. Lopez-Sanjuan, J. M. Diego, L.A. Diaz-Garcia, J. M. Vilchez, A. Lumbreras-Calle, D. Fernandez Gil, S. Gurung-Lopez, Y. Jimenez-Teja, A. Ederoclite, R. M. Gonzalez Delgado, H. Vazquez Ramio, R. Abramo, J. Alcaniz, N. Benitez, S. Bonoli, S. Carneiro, J. Cenarro, D. Cristobal-Hornillos, R. Dupke, C. Hernandez-Monteagudo, A. Marin-Franch, C. Mendes de Oliveira, M. Moles, L. Sodre Jr., K. Taylor, J. Varela ยท 2025

We report the discovery of a massive and potentially largest Ly$\alpha$ Nebula, RaJav, at z=2.25, associated with a quasar pair: the bright SDSS~J162029.07+433451.1 (hereafter J1620+4334) and the fainโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Improved Bounds on Access-Redundancy Tradeoffs in Quantized Linear Computations

Ching-Fang Li, Mary Wootters ยท 2025

Consider the problem of computing quantized linear functions with only a few queries. Formally, given $\mathbf{x}\in \mathbb{R}^k$, our goal is to encode $\mathbf{x}$ as $\mathbf{c} \in \mathbb{R}^n$,โ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

On Supports for graphs of bounded genus

Rajiv Raman, Karamjeet Singh ยท 2025

Let $(X,\mathcal{E})$ be a hypergraph. A support is a graph $Q$ on $X$ such that for each $E\in\mathcal{E}$, the subgraph of $Q$ induced on the elements in $E$ is connected. We consider the problem ofโ€ฆ

Read Paper โ†’
Engineering Preprint PDF DOI

A Risk-Averse Just-In-Time Scheme for Learning-Based Operation of Microgrids with Coupled Electricity-Hydrogen-Ammonia under Uncertainties

Longyan Li, Chao Ning, Guangsheng Pan, Leiqi Zhang, Wei Gu, Liang Zhao, Wenli Du, Mohammad Shahidehpour ยท 2024

This paper proposes a Risk-Averse Just-In-Time (RAJIT) operation scheme for Ammonia-Hydrogen-based Micro-Grids (AHMGs) to boost electricity-hydrogen-ammonia coupling under uncertainties. First, an offโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Data-Driven Symbol Detection for Intersymbol Interference Channels with Bursty Impulsive Noise

Boris Karanov, Chin-Hung Chen, Yan Wu, Alex Young, Wim van Houtum ยท 2024

We developed machine learning approaches for data-driven trellis-based soft symbol detection in coded transmission over intersymbol interference (ISI) channels in presence of bursty impulsive noise (Iโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Random Gabidulin Codes Achieve List Decoding Capacity in the Rank Metric

Zeyu Guo, Chaoping Xing, Chen Yuan, Zihan Zhang ยท 2024

Gabidulin codes, serving as the rank-metric counterpart of Reed-Solomon codes, constitute an important class of maximum rank distance (MRD) codes. However, unlike the fruitful positive results about tโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Graph Neural Network-based Joint Equalization and Decoding

Jannis Clausius, Marvin Geiselhart, Daniel Tandler, Stephan ten Brink ยท 2024

This paper proposes to use graph neural networks (GNNs) for equalization, that can also be used to perform joint equalization and decoding (JED). For equalization, the GNN is build upon the factor graโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

On the Robustness of Deep Learning-aided Symbol Detectors to Varying Conditions and Imperfect Channel Knowledge

Chin-Hung Chen, Boris Karanov, Wim van Houtum, Wu Yan, Alex Young, Alex Alvarado ยท 2024

Recently, a data-driven Bahl-Cocke-Jelinek-Raviv (BCJR) algorithm tailored to channels with intersymbol interference has been introduced. This so-called BCJRNet algorithm utilizes neural networks to cโ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

On generalized Sidon spaces

Chiara Castello ยท 2023

Sidon spaces have been introduced by Bachoc, Serra and Z\'emor as the $q$-analogue of Sidon sets, classical combinatorial objects introduced by Simon Szidon. In 2018 Roth, Raviv and Tamo introduced thโ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

The Riemann Hypothesis for period polynomials of cusp forms

William Craig, Wissam Raji ยท 2023

We consider the period polynomials $r_f(z)$ associated with cusp forms $f$ of weight $k$ on all of $\mathrm{SL}_2\left( \mathbb{Z} \right)$, which are generating functions for the critical $L$-values โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Approximate Private Inference in Quantized Models

Zirui Deng, Netanel Raviv ยท 2023

Private inference refers to a two-party setting in which one has a model (e.g., a linear classifier), the other has data, and the model is to be applied over the data while safeguarding the privacy ofโ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

Constructions and equivalence of Sidon spaces

Chiara Castello, Olga Polverino, Paolo Santonastaso, Ferdinando Zullo ยท 2023

Sidon spaces have been introduced by Bachoc, Serra and Z\'emor in 2017 as the $q$-analogue of Sidon sets. The interest on Sidon spaces has increased quickly, especially after the work of Roth, Raviv aโ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

Symmetries of the Black-Scholes-Merton equation for European options

Landysh N. Bakirova, Marina A. Shurygina, Vadim V. Shurygin, Jr ยท 2022

The aim of the present paper is the clarification of the result of A. Paliathanasis, K. Krishnakumar, K.M. Tamizhmani and P.G.L. Leach on the symmetry Lie algebra of the Black-Scholes-Merton equation โ€ฆ

Read Paper โ†’
Mathematics Preprint PDF DOI

L-values of harmonic Maass forms

Nikolaos Diamantis, Larry Rolen ยท 2022

Bruinier, Funke, and Imamoglu have proved a formula for what can philosophically be called the "central $L$-value" of the modular $j$-invariant. Previously, this had been heuristically suggested by Zaโ€ฆ

Read Paper โ†’
Page 1 of 3 Next โ†’