Related papers: An Improved Analytical Expression for Write Amplif…
The problem of variable-rate lossless data compression is considered, for codes with and without prefix constraints. Sharp bounds are derived for the best achievable compression rate of memoryless sources, when the excess-rate probability…
Transformers and large language models (LLMs), powered by the attention mechanism, have transformed numerous AI applications, driving the need for specialized hardware accelerators. A major challenge in these accelerators is efficiently…
Reliable causal effect estimation from observational data requires adjustment for confounding and sufficient overlap in covariate distributions between treatment groups. However, in high-dimensional settings, lack of overlap often inflates…
Nested weighted automata (NWA) present a robust and convenient automata-theoretic formalism for quantitative specifications. Previous works have considered NWA that processed input words only in the forward direction. It is natural to allow…
EXTRA is a popular method for dencentralized distributed optimization and has broad applications. This paper revisits EXTRA. First, we give a sharp complexity analysis for EXTRA with the improved…
Quantum search/amplitude amplification algorithms are designed to be able to amplify the amplitude in the target state linearly with the number of operations. Since the probability is the square of the amplitude, this results in the success…
Distribution of write error rate (WER) of spin-transfer-torque magnetoreistive random access memory (STT MRAM) caused by a distribution of resistance area product and anisotropy constant is theoretically studied. Assuming that WER is much…
This work proposes a mathematically founded mixed precision accumulation strategy for the inference of neural networks. Our strategy is based on a new componentwise forward error analysis that explains the propagation of errors in the…
This paper investigates the problem of variable-length lossy source coding allowing a positive excess distortion probability and an overflow probability of codeword lengths. Novel one-shot achievability and converse bounds of the optimal…
This paper summarizes our work on experimentally analyzing, exploiting, and addressing vulnerabilities in multi-level cell NAND flash memory programming, which was published in the industrial session of HPCA 2017, and examines the work's…
In this paper, we empirically analyze a simple, non-learnable, and nonparametric Nadaraya-Watson (NW) prediction head that can be used with any neural network architecture. In the NW head, the prediction is a weighted average of labels from…
Prices of NAND flash memories are falling drastically due to market growth and fabrication process mastering while research efforts from a technological point of view in terms of endurance and density are very active. NAND flash memories…
We examine the effect of clamping variables for approximate inference in undirected graphical models with pairwise relationships and discrete variables. For any number of variable labels, we demonstrate that clamping and summing approximate…
NAND flash memory is ubiquitous in everyday life today because its capacity has continuously increased and cost has continuously decreased over decades. This positive growth is a result of two key trends: (1) effective process technology…
The full-potential linearized augmented-plane wave (FP-LAPW) method is well known to enable most accurate calculations of the electronic structure and magnetic properties of crystals and surfaces. The implementation of atomic forces has…
We refit the NRL tight binding parameterization for Aluminium by Mehl \emph{et al} [Phys. Rev. B, 61, 4894 (2000)], to a database generated via full potential Linearized Augmented Plane Wave (LAPW) Density Functional Theory (DFT)…
Math Word Problem (MWP) solving presents a challenging task in Natural Language Processing (NLP). This study aims to provide MWP solvers with a more diverse training set, ultimately improving their ability to solve various math problems. We…
Doubly robust (DR) estimation is a crucial technique in causal inference and missing data problems. We propose a novel Propensity score Augmentved Doubly robust (PAD) estimator to enhance the commonly used DR estimator for average treatment…
Given data drawn from an unknown distribution, $D$, to what extent is it possible to ``amplify'' this dataset and output an even larger set of samples that appear to have been drawn from $D$? We formalize this question as follows: an…
Performance on the Winograd Schema Challenge (WSC), a respected English commonsense reasoning benchmark, recently rocketed from chance accuracy to 89% on the SuperGLUE leaderboard, with relatively little corroborating evidence of a…