Collections in this community

  • CS Technical Reports

    Technical Reports Archive for the Department of Computer Sciences at the University of Wisconsin-Madison
  • DMI Technical Reports

    DMI Technical Reports Archive for the Department of Computer Sciences at the University of Wisconsin-Madison
  • Math Prog Technical Reports

    Math Prog Technical Reports Archive for the Department of Computer Sciences at the University of Wisconsin-Madison

Recent Submissions

  • Understanding Representation Learning Paradigms with Applications to Low Resource Text Classification 

    Garg, Siddhant (2020-05-21)
    A crucial component of modern machine learning systems is learning input representations which can be used for prediction tasks. The expensive cost of labelling and easy availability of unlabelled data has led to the ...
  • Prioritize Winter Crash Severity Influencing Factors in US Midwestern for Autonomous Vehicle 

    Dai, Shenghong (2020-02-28)
    Adverse weather conditions in winter have significant impacts on crash occurrences and risks. Human drivers can adjust driving styles based on the context information of the surrounding traffic and environments. Similar ...
  • A New Semantic Approach on Yelp Review-star Rating Classification 

    Wu, Shuang; Wang, Xiaodong; Qi, Bozhao (2020-02-26)
    This paper introduces a new semantic approach for yelp review star rating prediction. Our approach extracts feature vectors from user reviews to develop star prediction models. User review text contains detailed information ...
  • On the Geometric and Statistical Interpretation of Data Augmentation 

    Feng, Zhili (2019-05-10)
    Data augmentation (DA) is a common technique in training machine learning models. For example in image classifications, people augment image datasets by random cropping, rotating, and adding random noises. Another trending ...
  • Improving Regulatory Network Reconstruction Through Topological Priors, Robust Hyperparameter Exploration, and Multi-Task Learning 

    Periyasamy, Viswesh (2019-05-10)
    Regulatory network reconstruction is an ongoing field of research that biologists have been pressing with considerable effort. Although several computational methods have been investigated, inferred networks still severely ...
  • Sensor-Based Risk Perception for Drivers Under Adverse Environment 

    Zhao, Wei (2018-08-18)
    Due to factors such as snow and ice impeding drivers’ vision, automobile accidents significantly rise during winter months. This study sets forth an automated evaluation network of the Risk Perceived Ability (RPA) for ...
  • Dynamic Query Re-Planning Using QOOP 

    Mahajan, Kshiteej; Chowdhury, Mosharaf; Akella, Aditya; Chawla, Shuchi (2018-09-27)
    Modern data processing clusters are highly dynamic – both in terms of the number of concurrently running jobs and their resource usage. To improve job performance, recent works have focused on optimizing the cluster scheduler ...
  • Exploration on Deep Drug Discovery: Representation and Learning 

    Liu, Shengchao (2018-09-20)
    Virtual (computational) high-throughput screening provides a strategy for prioritizing compounds for experimental screens, but the choice of virtual screening algorithm depends on the dataset and evaluation strategy. We ...
  • A Formula That Generates Hash Collisions 

    Brockmann, Andrew (2018-08-08)
    We present an explicit formula that produces hash collisions for the Merkle-Damgard construction. The formula works for arbitrary choice of message block and irrespective of the standardized constants used in hash functions, ...
  • Overreliance on Classical Computing in Quantum Factorization 

    Brockmann, Andrew (2018-08-08)
    A 2012 quantum experiment factored 143 after performing some simplifications classically. Further research demonstrated that that experiment arguably performed the quantum factorizations of other numbers too, such as 56153. ...
  • Deep Learning for Entity Matching: A Design Space Exploration 

    Mudgal Sunil Kumar, Sidharth (2018-05-15)
    Entity matching (EM) finds data instances that refer to the same real-world entity. In this thesis we examine applying deep learning (DL) to EM, to understand DL's benefits and limitations. We review many DL solutions that ...
  • Error Backprojection Algorithms for Non-Line-of-Sight Imaging 

    La Manna, Marco; Kine, Fiona; Breitbach, Eric; Jackson, Jonathan; Velten, Andreas (2017-10-18)
    Recent advances in computer vision and inverse light transport theory have resulted in several non-line-of-sight imaging techniques. These techniques use photon time-of-flight information encoded in light after multiple, ...
  • What Are Optimal Coding Functions for Time-of-Flight Imaging? 

    Gupta, Mohit; Velten, Andreas; Nayer, Shree; Breitbach, Eric (2017-06-26)
    The depth resolution achieved by a continuous wave time-of-flight (C-ToF) imaging system is determined by the coding (modulation and demodulation) functions that it uses. Almost all current C-ToF systems use sinusoid or ...
  • Quickstep: A Data Platform Based on the Scaling-In Approach 

    Jignesh M. Patel; Harshad Deshmukh; Jianqiao Zhu; Hakan Memisoglu; Navneet Potti; Saket Saurabh; Marc Spehlmann; Zuyu Zhang (2017-06-19)
    Modern servers pack enough storage and computing power that just a decade ago was spread across a modest- sized cluster. This paper presents a prototype system, called Quickstep, to exploit the large amount of paral- lelism ...
  • A New Abstraction Framework for Affine Transformers 

    Reps, Thomas; Sharma, Tushar (2017-05-16)
    Abstract. This paper addresses the problem of abstracting a set of affine transformers v' = v C + d, where v and v' represent the pre-state and post-state, respectively. We introduce a framework to harness any base abstract ...
  • Supporting Proofs for Control-Flow Recovery from Partial Failure Reports 

    Ohmann, Peter; Brooks, Alexander; D'Antoni, Loris; Liblit, Ben (2017-04-28)
    Debugging post-deployment failures is difficult, in part because failure reports from these applications usually provide only partial information about what occurred during the failing execution. We introduce approaches ...
  • Clarinet: WAN-Aware Optimization for Analytics Queries 

    Viswanathan, Raajay; Ananthanarayanan, Ganesh; Akella, Aditya (2017-03-08)
    Recent work has made the case for geo-distributed analytics, where data collected and stored at multiple datacenters and edge sites world-wide is analyzed in situ to drive operational and management decisions. A key issue ...
  • Dissolve: A Distributed SAT Solver Based on Stalmarck's Method 

    Henry, Julien; Thakur, Aditya; Kidd, Nicholas; Reps, Thomas (2017-03-08)
    Creating an effective parallel SAT solver is known to be a challenging task. At present, the most efficient implementations of parallel SAT solvers are portfolio solvers with some heuristics to share learnt clauses. In ...
  • Compositional Recurrence Analysis Revisited 

    Kincaid, Zachary; Breck, Jason; Forouhi Boroujeni, Ashkan; Reps, Thomas (2017-03-08)
    Compositional recurrence analysis (CRA) is a static-analysis method based on a combination of symbolic analysis and abstract interpretation. This paper addresses the problem of creating a context-sensitive interprocedural ...
  • Some Submodular Data-Poisoning Attacks on Machine Learners 

    Mei, Shike; Zhu, Xiaojin (2017-03-08)
    We study data-poisoning attacks using a machine teaching framework. For a family of NP-hard attack problems we pose them as submodular function maximization, thereby inheriting efficient greedy algorithms with theoretical ...

View more