activity
20162024
most citedEmbedDistill: A Geometric Knowledge Distillation for Information Retrieval

4 citations · 10 across the 4 of their papers we have counts for

collaborators

7 papers

cs.LG2024★ 1 cited

A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs

Ankit Singh Rawat, Veeranjaneyulu Sadhanala, Afshin Rostamizadeh +12

A primary challenge in large language model (LLM) development is their onerous pre-training cost. Typically, such pre-training involves optimizing a self-supervised objective (such…

cs.LG2023★ 4 cited

EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval

Seungyeon Kim, Ankit Singh Rawat, Manzil Zaheer +6

Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR). In this paper, we aim to improve distillation methods that pave the…

math.ST2022★ 2 cited

Exponential Family Trend Filtering on Lattices

Veeranjaneyulu Sadhanala, Robert Bassett, James Sharpnack +1

Trend filtering is a modern approach to nonparametric regression that is more adaptive to local smoothness than splines or similar basis procedures. Existing analyses of trend filt…

stat.ML2021

Multivariate Trend Filtering for Lattice Data

Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Addison J. Hu +1

We study a multivariate version of trend filtering, called Kronecker trend filtering or KTF, for the case in which the design points form a lattice in dimensions. KTF is a natu…

stat.ML2019★ 3 cited

A Higher-Order Kolmogorov-Smirnov Test

Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Aaditya Ramdas +1

We present an extension of the Kolmogorov-Smirnov (KS) two-sample test, which can be more sensitive to differences in the tails. Our test statistic is an integral probability metri…

stat.ML2017

Additive Models with Trend Filtering

Veeranjaneyulu Sadhanala, Ryan J. Tibshirani

We study additive models built with trend filtering, i.e., additive models whose components are each regularized by the (discrete) total variation of their th (discrete) derivat…