1 citations · 1 across the 12 of their papers we have counts for
12 papers
Flash-SD-KDE: Accelerating SD-KDE with Tensor Cores
Elliot L. Epstein, Rajat Vadiraj Dwaraknath, John Winnicki
Score-debiased kernel density estimation (SD-KDE) achieves improved asymptotic convergence rates over classical KDE, but its use of an empirical score has made it significantly slo…
Allocate Marginal Reviews to Borderline Papers Using LLM Comparative Ranking
Elliot L. Epstein, Rajat Dwaraknath, John Winnicki +1
This paper argues that large ML conferences should allocate marginal review capacity primarily to papers near the acceptance boundary, rather than spreading extra reviews via rando…
FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUs
Rajat Vadiraj Dwaraknath, Sungyoon Kim, Mert Pilanci
Sparse sketches such as the sparse Johnson-Lindenstrauss transform are a core primitive in randomized numerical linear algebra because they leverage random sparsity to reduce the a…
Sampling on Metric Graphs
Rajat Vadiraj Dwaraknath, Lexing Ying
Metric graphs are structures obtained by associating edges in a standard graph with segments of the real line and gluing these segments at the vertices of the graph. The resulting…
LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval
Elliot L. Epstein, John Winnicki, Thanawat Sornwanee +1
Large language models (LLMs) excel at numerical estimation but struggle to correctly quantify uncertainty. We study how well LLMs construct confidence intervals around their own an…
Variational inference and density estimation with non-negative tensor train
Xun Tang, Rajat Dwaraknath, Lexing Ying
This work proposes an efficient numerical approach for compressing a high-dimensional discrete distribution function into a non-negative tensor train (NTT) format. The two settings…
MatRL: Provably Generalizable Iterative Algorithm Discovery via Monte-Carlo Tree Search
Sungyoon Kim, Rajat Vadiraj Dwaraknath, Longling geng +1
Iterative methods for computing matrix functions have been extensively studied and their convergence speed can be significantly improved with the right tuning of parameters and by…
BWLer: Barycentric Weight Layer Elucidates a Precision-Conditioning Tradeoff for PINNs
Jerry Liu, Yasa Baig, Denise Hui Jean Lee +3
Physics-informed neural networks (PINNs) offer a flexible way to solve partial differential equations (PDEs) with machine learning, yet they still fall well short of the machine-pr…
SD-KDE: Score-Debiased Kernel Density Estimation
Elliot L. Epstein, Rajat Dwaraknath, Thanawat Sornwanee +2
We propose a novel method for density estimation that leverages an estimated score function to debias kernel density estimation (SD-KDE). In our approach, each data point is adjust…
Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs
Rajat Vadiraj Dwaraknath, Tolga Ergen, Mert Pilanci
Recently, theoretical analyses of deep neural networks have broadly focused on two directions: 1) Providing insight into neural network training by SGD in the limit of infinite hid…
Towards Optimal Effective Resistance Estimation
Rajat Vadiraj Dwaraknath, Ishani Karmarkar, Aaron Sidford
We provide new algorithms and conditional hardness for the problem of estimating effective resistances in -node -edge undirected, expander graphs. We provide an $\widetilde{O…
[Reproducibility Report] Rigging the Lottery: Making All Tickets Winners
Varun Sundar, Rajat Vadiraj Dwaraknath
, a sparse training algorithm, claims to directly train sparse networks that match or exceed the performance of existing dense-to-sparse training techniques (such as…