@article{pop00001,
author = {B Isik and K Choi and X Zheng and T Weissman and S Ermon and ...},
title = {Neural network compression for noisy storage devices},
journal = {arXiv preprint arXiv …},
publisher = {arxiv.org},
url = {https://arxiv.org/abs/2102.07725},
fulltext = {https://arxiv.org/pdf/2102.07725},
related = {https://scholar.google.com/scholar?q=related:j8W1iY9G37IJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2021},
abstract = {Compression and efficient storage of neural network (NN) parameters is critical for applications that run on resource-constrained devices. Although NN model compression has made significant progress, there has been considerably less investigation in the actual …}
}
@article{pop00002,
author = {B Isik and A No and T Weissman},
title = {Successive pruning for model compression via rate distortion theory},
journal = {arXiv preprint arXiv:2102.08329},
publisher = {arxiv.org},
url = {https://arxiv.org/abs/2102.08329},
fulltext = {https://arxiv.org/pdf/2102.08329},
related = {https://scholar.google.com/scholar?q=related:GfkwnVCdBh0J:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2021},
abstract = {Neural network (NN) compression has become essential to enable deploying over-parameterized NN models on resource-constrained devices. As a simple and easy-to-implement method, pruning is one of the most established NN compression techniques …}
}
@article{pop00003,
author = {Y Han and K Tatwawadi and GR Kurri and Z Zhou and ...},
title = {Optimal Communication Rates and Combinatorial Properties for Common Randomness Generation},
journal = {IEEE Transactions …},
publisher = {ieeexplore.ieee.org},
url = {https://ieeexplore.ieee.org/abstract/document/9570391/},
fulltext = {https://ieeexplore.ieee.org/iel7/18/4667673/09570391.pdf},
year = {2021},
abstract = {We study common randomness generation problems where n players aim to generate same sequences of random coin flips where some subsets of the players share an independent common coin which can be tossed multiple times, and there is a publicly seen blackboard …}
}
@article{pop00004,
author = {P Tandon and S Chandak and P Pataranutaporn and Y Liu and ...},
title = {Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text},
journal = {arXiv preprint arXiv …},
publisher = {arxiv.org},
url = {https://arxiv.org/abs/2106.14014},
fulltext = {https://arxiv.org/pdf/2106.14014},
year = {2021},
abstract = {Video represents the majority of internet traffic today leading to a continuous technological arms race between generating higher quality content, transmitting larger file sizes and supporting network infrastructure. Adding to this is the recent COVID-19 pandemic fueled …}
}
@article{pop00005,
author = {W Zhang and B Kitts and Y Han and Z Zhou and T Mao and H He and ...},
title = {MEOW: A Space-Efficient Nonparametric Bid Shading Algorithm},
journal = {Proceedings of the 27th …},
publisher = {dl.acm.org},
doi = {10.1145/3447548.3467113},
url = {https://dl.acm.org/doi/abs/10.1145/3447548.3467113},
fulltext = {https://dl.acm.org/doi/pdf/10.1145/3447548.3467113},
year = {2021},
abstract = {Bid Shading has become increasingly important in Online Advertising, with a large amount of commercial [4, 12, 13, 29] and research work [11, 20, 28] recently published. Most approaches for solving the bid shading problem involve estimating the probability of win …}
}
@article{pop00006,
author = {BT Lau and S Chandak and S Roy and K Tatawadi and M Wootters and ...},
title = {Magnetic DNA random access memory with nanopore readouts and exponentially-scaled combinatorial addressing},
journal = {bioRxiv},
publisher = {biorxiv.org},
doi = {10.1101/2021.09.15.460571.abstract},
url = {https://www.biorxiv.org/content/10.1101/2021.09.15.460571.abstract},
fulltext = {https://www.biorxiv.org/content/biorxiv/early/2021/09/16/2021.09.15.460571.full.pdf},
year = {2021},
abstract = {The storage of data in DNA typically involves encoding and synthesizing data into short oligonucleotides, followed by reading with a sequencing instrument. Major challenges include the molecular consumption of synthesized DNA, issues with basecalling errors, and …}
}
@article{pop00007,
author = {Q Meng and S Chandak and Y Zhu and T Weissman},
title = {NanoSpring: reference-free lossless compression of nanopore sequencing reads using an approximate assembly approach},
journal = {bioRxiv},
publisher = {biorxiv.org},
doi = {10.1101/2021.06.09.447198v1.abstract},
url = {https://www.biorxiv.org/content/10.1101/2021.06.09.447198v1.abstract},
fulltext = {https://www.biorxiv.org/content/biorxiv/early/2021/06/10/2021.06.09.447198.full.pdf},
related = {https://scholar.google.com/scholar?q=related:un0MBEeyWn4J:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2021},
abstract = {Motivation: The amount of data produced by genome sequencing experiments has been growing rapidly over the past several years, making compression important for efficient storage, transfer and analysis of the data. In recent years, nanopore sequencing …}
}
@article{pop00008,
author = {DS Pavlichin and HJ Lee and SU Greer and SM Grimes and ...},
title = {KmerKeys: a web resource for searching indexed genome assemblies and variants},
journal = {bioRxiv},
publisher = {biorxiv.org},
doi = {10.1101/2021.05.17.444256v1.abstract},
url = {https://www.biorxiv.org/content/10.1101/2021.05.17.444256v1.abstract},
fulltext = {https://www.biorxiv.org/content/biorxiv/early/2021/05/18/2021.05.17.444256.full.pdf},
related = {https://scholar.google.com/scholar?q=related:qBp2EcOSbYYJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2021},
abstract = {K-mers are short DNA sequences that are used for genome sequence analysis. Applications that use k-mers include genome assembly and alignment. Despite these current applications, the wider bioinformatic use of k-mers in has challenges related to the massive …}
}
@article{pop00009,
author = {B Isik and A No and T Weissman},
title = {Rate-Distortion Theoretic Model Compression: Successive Refinement for Pruning},
journal = {arXiv preprint arXiv:2102.08329},
publisher = {128.84.4.34},
url = {http://128.84.4.34/abs/2102.08329},
year = {2021},
abstract = {We study the neural network (NN) compression problem, viewing the tension between the compression ratio and NN performance through the lens of rate-distortion theory. We choose a distortion metric that reflects the effect of NN compression on the model output and then …}
}
@article{pop00010,
author = {Y Han and J Jiao and T Weissman and Y Wu},
title = {Optimal rates of entropy estimation over Lipschitz balls},
journal = {The Annals of Statistics},
publisher = {projecteuclid.org},
doi = {10.1214/19-AOS1927.short},
url = {https://projecteuclid.org/journals/annals-of-statistics/volume-48/issue-6/Optimal-rates-of-entropy-estimation-over-Lipschitz-balls/10.1214/19-AOS1927.short},
fulltext = {https://arxiv.org/pdf/1711.02141},
related = {https://scholar.google.com/scholar?q=related:U0WvjixkUAMJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {We consider the problem of minimax estimation of the entropy of a density over Lipschitz balls. Dropping the usual assumption that the density is bounded away from zero, we obtain the minimax rates $(n\\ln n)^\{-s/(s+ d)\}+ n^\{-1/2\} $ for $0< s\\leq 2$ for densities supported on …}
}
@article{pop00011,
author = {Y Han and J Jiao and T Weissman},
title = {Minimax estimation of divergences between discrete distributions},
journal = {IEEE Journal on Selected Areas in …},
publisher = {ieeexplore.ieee.org},
url = {https://ieeexplore.ieee.org/abstract/document/9273044/},
fulltext = {https://ieeexplore.ieee.org/iel7/8700143/9035652/09273044.pdf},
related = {https://scholar.google.com/scholar?q=related:m8XvCmLP5XMJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {We study the minimax estimation of $\\alpha $-divergences between discrete distributions for integer $\\alpha\\ge 1$, which include the Kullback–Leibler divergence and the $\\chi^\{2\} $-divergences as special examples. Dropping the usual theoretical tricks to acquire …}
}
@article{pop00012,
author = {J Mardia and J Jiao and E Tánczos and RD Nowak and ...},
title = {Concentration inequalities for the empirical distribution of discrete distributions: beyond the method of types},
journal = {… and Inference: A …},
publisher = {academic.oup.com},
url = {https://academic.oup.com/imaiai/article-abstract/9/4/813/5627733},
related = {https://scholar.google.com/scholar?q=related:dxOGXnuy2ikJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {We study concentration inequalities for the Kullback–Leibler (KL) divergence between the empirical distribution and the true distribution. Applying a recursion technique, we improve over the method of types bound uniformly in all regimes of sample size and alphabet size …}
}
@article{pop00013,
author = {S Chandak and J Neu and K Tatwawadi and ...},
title = {Overcoming high nanopore basecaller error rates for DNA storage via basecaller-decoder integration and convolutional codes},
journal = {ICASSP 2020-2020 …},
publisher = {ieeexplore.ieee.org},
url = {https://ieeexplore.ieee.org/abstract/document/9053441/},
fulltext = {https://ieeexplore.ieee.org/iel7/9040208/9052899/09053441.pdf},
related = {https://scholar.google.com/scholar?q=related:qcHLPUwBk9EJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {As magnetization and semiconductor based storage technologies approach their limits, bio-molecules, such as DNA, have been identified as promising media for future storage systems, due to their high storage density (petabytes/gram) and long-term durability …}
}
@article{pop00014,
author = {S Chandak and K Tatwawadi and S Sridhar and ...},
title = {Impact of lossy compression of nanopore raw signal data on basecalling and consensus accuracy},
journal = {Bioinformatics},
publisher = {academic.oup.com},
url = {https://academic.oup.com/bioinformatics/article-abstract/36/22-23/5313/6039112},
fulltext = {https://academic.oup.com/bioinformatics/article/36/22-23/5313/6039112},
related = {https://scholar.google.com/scholar?q=related:vtm52GKiRhQJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {Motivation Nanopore sequencing provides a real-time and portable solution to genomic sequencing, enabling better assembly, structural variant discovery and modified base detection than second generation technologies. The sequencing process generates a huge …}
}
@article{pop00015,
author = {S Chandak and K Tatwawadi and C Wen and ...},
title = {LFZip: Lossy compression of multivariate floating-point time series data via improved prediction},
journal = {2020 Data …},
publisher = {ieeexplore.ieee.org},
url = {https://ieeexplore.ieee.org/abstract/document/9105816/},
fulltext = {https://ieeexplore.ieee.org/iel7/9102212/9105663/09105816.pdf},
related = {https://scholar.google.com/scholar?q=related:-XCpcV6IP1gJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {Time series data compression is emerging as an important problem with the growth in IoT devices and sensors. Due to the presence of noise in these datasets, lossy compression can often provide significant compression gains without impacting the performance of …}
}
@article{pop00016,
author = {Y Han and Z Zhou and A Flores and E Ordentlich and ...},
title = {Learning to Bid Optimally and Efficiently in Adversarial First-price Auctions},
journal = {arXiv preprint arXiv …},
publisher = {arxiv.org},
url = {https://arxiv.org/abs/2007.04568},
fulltext = {https://arxiv.org/pdf/2007.04568},
related = {https://scholar.google.com/scholar?q=related:kDVnZ60UmYsJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {First-price auctions have very recently swept the online advertising industry, replacing second-price auctions as the predominant auction mechanism on many platforms. This shift has brought forth important challenges for a bidder: how should one bid in a first-price …}
}
@article{pop00017,
author = {Y Han and Z Zhou and T Weissman},
title = {Optimal no-regret learning in repeated first-price auctions},
journal = {arXiv preprint arXiv:2003.09795},
publisher = {arxiv.org},
url = {https://arxiv.org/abs/2003.09795},
fulltext = {https://arxiv.org/pdf/2003.09795},
related = {https://scholar.google.com/scholar?q=related:m3smN8wtzcEJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {We study online learning in repeated first-price auctions with censored feedback, where a bidder, only observing the winning bid at the end of each auction, learns to adaptively bid in order to maximize her cumulative payoff. To achieve this goal, the bidder faces a …}
}
@article{pop00018,
author = {R Prabhakar and S Chandak and C Chiu and R Liang and ...},
title = {Reducing latency and bandwidth for video streaming using keypoint extraction and digital puppetry},
journal = {arXiv preprint arXiv …},
publisher = {arxiv.org},
url = {https://arxiv.org/abs/2011.03800},
fulltext = {https://arxiv.org/pdf/2011.03800},
related = {https://scholar.google.com/scholar?q=related:KWqOM_2va_QJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {COVID-19 has made video communication one of the most important modes of information exchange. While extensive research has been conducted on the optimization of the video streaming pipeline, in particular the development of novel video codecs, further …}
}
@book{pop00019,
author = {B Isik and K Choi and X Zheng and HSP Wong and S Ermon and ...},
title = {Noisy Neural Network Compression for Analog Storage Devices},
publisher = {openreview.net},
url = {https://openreview.net/forum?id=APvrboUZS7w},
fulltext = {https://openreview.net/pdf?id=APvrboUZS7w},
related = {https://scholar.google.com/scholar?q=related:IHFSFBuPcxcJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2020},
abstract = {Efficient compression and storage of neural network (NN) parameters is critical for resource-constrained, downstream machine learning applications. Although several methods for NN compression have been developed, there has been considerably less work in the efficient …}
}
@article{pop00020,
author = {S Chandak and KS Tatwawadi and T Weissman and ...},
title = {Systems and Methods for Compressing Genetic Sequencing Data and Uses Thereof},
journal = {US Patent App. 16 …},
publisher = {Google Patents},
url = {https://patents.google.com/patent/US20200058379A1/en},
fulltext = {https://patentimages.storage.googleapis.com/17/9f/70/c527656ea060ed/US20200058379A1.pdf},
year = {2020}
}
@article{pop00021,
author = {S Chandak and K Tatwawadi and I Ochoa and M Hernaez and ...},
title = {SPRING: a next-generation compressor for FASTQ data},
journal = {…},
publisher = {academic.oup.com},
url = {https://academic.oup.com/bioinformatics/article-abstract/35/15/2674/5232998},
fulltext = {https://academic.oup.com/bioinformatics/article/35/15/2674/5232998},
related = {https://scholar.google.com/scholar?q=related:jsqj6uaX4d8J:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {Abstract Motivation High-Throughput Sequencing technologies produce huge amounts of data in the form of short genomic reads, associated quality values and read identifiers. Because of the significant structure present in these FASTQ datasets, general-purpose …}
}
@article{pop00022,
author = {DS Pavlichin and J Jiao and T Weissman},
type = {PDF},
title = {Approximate Profile Maximum Likelihood.},
journal = {J. Mach. Learn. Res.},
publisher = {jmlr.org},
url = {https://www.jmlr.org/papers/volume20/18-075/18-075.pdf},
fulltext = {https://www.jmlr.org/papers/volume20/18-075/18-075.pdf},
related = {https://scholar.google.com/scholar?q=related:HAbG1i6G7uEJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {We propose an efficient algorithm for approximate computation of the profile maximum likelihood (PML), a variant of maximum likelihood maximizing the probability of observing a sufficient statistic rather than the empirical sample. The PML has appealing theoretical …}
}
@article{pop00023,
author = {K Choi and K Tatwawadi and A Grover and ...},
title = {Neural joint source-channel coding},
journal = {International …},
publisher = {proceedings.mlr.press},
url = {http://proceedings.mlr.press/v97/choi19a.html},
fulltext = {http://proceedings.mlr.press/v97/choi19a/choi19a.pdf},
related = {https://scholar.google.com/scholar?q=related:oNf8M0HBBbgJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes. However, this decomposition can fall short in the finite bit-length …}
}
@article{pop00024,
author = {M Hernaez and D Pavlichin and T Weissman and ...},
title = {Genomic data compression},
journal = {Annual Review of …},
publisher = {annualreviews.org},
doi = {10.1146/annurev-biodatasci-072018-021229},
url = {https://www.annualreviews.org/doi/abs/10.1146/annurev-biodatasci-072018-021229},
fulltext = {https://www.annualreviews.org/doi/full/10.1146/annurev-biodatasci-072018-021229},
related = {https://scholar.google.com/scholar?q=related:FHLPWGPWIccJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {Recently, there has been growing interest in genome sequencing, driven by advances in sequencing technology, in terms of both efficiency and affordability. These developments have allowed many to envision whole-genome sequencing as an invaluable tool for both …}
}
@article{pop00025,
author = {S Chandak and K Tatwawadi and B Lau and ...},
title = {Improved read/write cost tradeoff in DNA-based data storage using LDPC codes},
journal = {2019 57th Annual …},
publisher = {ieeexplore.ieee.org},
url = {https://ieeexplore.ieee.org/abstract/document/8919890/},
fulltext = {https://ieeexplore.ieee.org/iel7/8911248/8919648/08919890.pdf},
related = {https://scholar.google.com/scholar?q=related:tpSGAa8zjDQJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {With the amount of data being stored increasing rapidly, there is significant interest in exploring alternative storage technologies. In this context, DNA-based storage systems can offer significantly higher storage densities (petabytes/gram) and durability (thousands of …}
}
@article{pop00026,
author = {J Jiao and Y Han and I Fischer-Hwang and ...},
title = {Estimating the fundamental limits is easier than achieving the fundamental limits},
journal = {IEEE Transactions on …},
publisher = {ieeexplore.ieee.org},
url = {https://ieeexplore.ieee.org/abstract/document/8758354/},
fulltext = {https://ieeexplore.ieee.org/iel7/18/4667673/08758354.pdf},
related = {https://scholar.google.com/scholar?q=related:Ybe0OA9GdOkJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {We show through case studies that it is easier to estimate the fundamental limits of data processing than to construct the explicit algorithms to achieve those limits. Focusing on binary classification, data compression, and prediction under logarithmic loss, we show that …}
}
@article{pop00027,
author = {I Fischer-Hwang and I Ochoa and T Weissman and M Hernaez},
type = {HTML},
title = {Denoising of aligned genomic data},
journal = {Scientific reports},
publisher = {nature.com},
url = {https://www.nature.com/articles/s41598-019-51418-z},
fulltext = {https://www.nature.com/articles/s41598-019-51418-z},
related = {https://scholar.google.com/scholar?q=related:hs2v5o_D10cJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {Noise in genomic sequencing data is known to have effects on various stages of genomic data analysis pipelines. Variant identification is an important step of many of these pipelines, and is increasingly being used in clinical settings to aid medical practices. We propose a …}
}
@article{pop00028,
author = {I Fischer-Hwang and Z Lu and J Zou and T Weissman},
title = {Cross-linked RNA secondary structure analysis using network techniques},
journal = {bioRxiv},
publisher = {biorxiv.org},
doi = {10.1101/668491v1.abstract},
url = {https://www.biorxiv.org/content/10.1101/668491v1.abstract},
fulltext = {https://www.biorxiv.org/content/biorxiv/early/2019/06/12/668491.full.pdf},
related = {https://scholar.google.com/scholar?q=related:N3W95MP6V9sJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {Next generation sequencing and biochemical cross-linking methods have been combined into powerful tools to probe RNA secondary structure. One such method, known as PARIS, has been used to produce near base-pair maps of long-range and alternative RNA …}
}
@article{pop00029,
author = {DS Pavlichin and Y Quek and T Weissman},
title = {Minimum Power to Maintain a Nonequilibrium Distribution of a Markov Chain},
journal = {arXiv preprint arXiv:1907.01582},
publisher = {arxiv.org},
url = {https://arxiv.org/abs/1907.01582},
fulltext = {https://arxiv.org/pdf/1907.01582},
related = {https://scholar.google.com/scholar?q=related:tzKFKFRo45EJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {Biological systems use energy to maintain non-equilibrium distributions for long times, eg of chemical concentrations or protein conformations. What are the fundamental limits of the power used to" hold" a stochastic system in a desired distribution over states? We study the …}
}
@article{pop00030,
author = {Y Han and K Tatwawadi and GR Kurri and Z Zhou and ...},
title = {Optimal Communication Rates and Combinatorial Properties for Distributed Simulation},
journal = {arXiv preprint arXiv …},
publisher = {arxiv.org},
url = {https://arxiv.org/abs/1904.03271},
fulltext = {https://arxiv.org/pdf/1904.03271},
related = {https://scholar.google.com/scholar?q=related:WYiN6nRplyEJ:scholar.google.com/\&scioq=author:%22tsachy+weissman%22\&hl=en\&as_sdt=2007},
year = {2019},
abstract = {We study the distributed simulation problem where $ n $ players aim to generate same sequences of random coin flips where some subsets of the players share an independent common coin which can be tossed multiple times, and there is a publicly seen blackboard …}
}
@article{pop00031,
author = {A Bhown and S Mukherjee and S Yang and ...},
title = {Humans are Still the Best Lossy Image Compressors},
journal = {2019 Data …},
publisher = {ieeexplore.ieee.org},
url = {https://ieeexplore.ieee.org/abstract/document/8712697/},
fulltext = {https://scholar.google.com/scholar?output=instlink\&q=info:feyKNha-LM4J:scholar.google.com/\&hl=en\&as_sdt=2007\&scillfp=14154986462239703300\&oi=lle},
year = {2019},
abstract = {Lossy image compression has been studied extensively in the context of typical loss functions such as RMSE, MS-SSIM, etc. However, it is not well understood what loss function might be most appropriate for human perception. Furthermore, the availability of massive …}
}
@article{pop00032,
author = {Y Han and K Tatwawadi and Z Zhou and GR Kurri and ...},
type = {CITATION},
title = {Optimal Communication Rates for Zero-Error Distributed Simulation under Blackboard Communication Protocols.},
journal = {CoRR},
year = {2019}
}
This file was generated by bibtex2html 1.98.