Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.04259

Hardware-conscious Software Training for Deep Neural Network Inference Accelerator Chips to Recover Accuracy Degradation due to Hardware Variabilities

Shuchao Gao·Takashi Ohsawa
View original source ↗Read source document ↗Export metadata ↓

Abstract

Deep neural network (DNN) has been widely applied in various industries. Specialized chips are being discussed for the purpose of achieving lower power consumption with higher throughput. Hardware variations introduced during the process of chip manufacturing are the main reason for affecting the inference accuracies. In this paper, we propose hardware-conscious software training (HCST) method which enables high inference accuracies even under the influence of hardware variations.

Explore related subjects

cs.ARcs.ET

Keep this discovery

BibTeXRIS

Shuchao Gao, Takashi Ohsawa. 2026-09-02. Hardware-conscious Software Training for Deep Neural Network Inference Accelerator Chips to Recover Accuracy Degradation due to Hardware Variabilities. https://doi.org/10.7567/ssdm.2023.j-5-03

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

cs.AR subjectcs.ET subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related papers

arXiv2026

The microscope is the mask: privileged views and labels from a cryo-ET forward model

We explore the use of simulated data for training a model for protein annotation in crowded cryo-electron tomography volumes reconstructed from images collected at limited tilt angles and severely corrupted by the measurement operator. Firstly, we leverage the corruptions imposed by the forward model to generate domain-specific augmented paired views of the exact same scene for an invariance objective integrated into the LeJEPA self-supervised training framework. Secondly, we use additional information from the simulation pipeline such as the positions and identity of proteins in the simulated volumes to inform the architecture of the model and the loss function, so that semantic information is localised at protein positions in the resulting dense feature volume. The resulting model, CARNIVAL, is evaluated without finetuning on classification and detection tasks in real tomograms, using a benchmark dataset containing multiple protein types and two tomogram processing types. We show that CARNIVAL outperforms a state-of-the-art model trained using a contrastive objective on simulated data but without forward model-based paired views or privileged information.

cs.CV↗
arXiv2026

A brief history of quantum vs classical computational advantage

In this review article we summarize all experiments claiming quantum computational advantage to date. Our review highlights challenges, loopholes, and refutations appearing in subsequent work to provide a complete picture of the current statuses of these experiments. In addition, we also discuss theoretical computational advantage in example problems such as approximate optimization and recommendation systems. Finally, we review recent experiments in quantum error correction -- the biggest frontier to reach experimental quantum advantage in Shor's algorithm.

quant-ph↗
arXiv2026

Redundancy rules for MaxSAT

The concept of redundancy in SAT leads to more expressive and powerful proof search techniques, e.g., able to express various inprocessing techniques, and originates interesting hierarchies of proof systems [Heule et$.$al'20, Buss-Thapen'19]. Redundancy has also been integrated in MaxSAT [Ihalainen et$.$al'22, Berg et$.$al'23, Bonacina et$.$al'24]. In this paper, we define a structured hierarchy of redundancy proof systems for MaxSAT, with the goal of studying its proof complexity. We obtain MaxSAT variants of proof systems such as SPR, PR, SR, and others, previously defined for SAT. All our rules are polynomially checkable, unlike [Ihalainen et$.$al'22]. Moreover, they are simpler and weaker than [Berg et$.$al'23], and possibly amenable to lower bounds. This work also complements the approach of [Bonacina et$.$al'24]. Their proof systems use different rule sets for soft and hard clauses, while here we propose a system using only hard clauses and blocking variables. This is easier to integrate with current solvers and proof checkers. We discuss the strength of the systems introduced, we show some limitations of them, and we give a short cost-SR proof that any assignment for the weak pigeonhole principle $PHP^{m}_{n}$ falsifies at least $m-n$ clauses. We conclude by discussing the integration of our rules with the MaxSAT resolution proof system, which is a commonly studied proof system for MaxSAT.

cs.LO↗