Publications Chronologically

[Back to Homepage]


  • Runtime Performance Anomaly Diagnosis in Production HPC Systems Using Active Learning
    Burak Aksar, Efe Sencan, Ben Schwaller, Omar Aaziz, Vitus J Leung, Jim Brandt, Brian Kulis, Manuel Egele, and Ayse K Coskun
    In IEEE Transactions on Parallel and Distributed Systems, Volume 35, Number 4, pp. 693-706, 2024.
    [ieee link]

  • Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning
    Christopher Liao, Theodoros Tsiligkaridis, and Brian Kulis
    In Proc.Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
    [arxiv link]

  • Maximum-Entropy Adversarial Audio Augmentation for Keyword Spotting
    Zuzhao Ye, Gregory Ciccarelli, and Brian Kulis
    In Proc. International Conference Acoustics, Speech, and Signal Processing (ICASSP), 2024.
    [arxiv link]

  • Prodigy: Towards unsupervised anomaly detection in production HPC systems
    Burak Aksar, Efe Sencan, Ben Schwaller, Vitus J Leung, Jim Brandt, Brian Kulis, Manuel Egele, and Ayse K Coskun
    In Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2023.
    [acm link]

  • Towards Practical Machine Learning Frameworks for Performance Diagnostics in Supercomputers
    Burak Aksar, Efe Sencan, Ben Schwaller, Vitus J Leung, Jim Brandt, Brian Kulis, Manuel Egele, and Ayse K Coskun
    In Proc. First Workshop on AI for Systems, 2023.
    [acm link]

  • Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization
    Christopher Liao, Theodoros Tsiligkaridis, and Brian Kulis
    In Proc. 40th International Conference on Machine Learning, 2023.
    [arxiv link]

  • ALBADross: Active Learning Based Anomaly Diagnosis for Production HPC Systems
    Burak Aksar, Efe Sencan, Benjamin Schwaller, Omar Aaziz, Vitus J Leung, Jim Brandt, Brian Kulis, Manuel Egele, and Ayse K Coskun
    In IEEE International Conference on Cluster Computing (CLUSTER), 2022.
    [web link]

  • Substitutional Neural Image Compression
    Xiao Wang, Ding Ding, Wei Jiang, Wei Wang, Xiaozhong Xu, Shan Liu, Brian Kulis, and Peter Chin
    In Picture Coding Symposium (PCS), 2022.
    [arxiv link]

  • Pick up the PACE: Fast and Simple Domain Adaptation via Ensemble Pseudo-Labeling
    Christopher Liao, Theodoros Tsiligkaridis, and Brian Kulis
    Arxiv: 2205.13508, 2022.
    [arxiv link]

  • Latency Control for Keyword Spotting
    Christin Jose, Joseph Wang, Grant Strimel, Mohammad Omar Khursheed, Yuriy Mishchenko, and Brian Kulis
    In Proc. 23rd INTERSPEECH Conference, 2022.
    [arxiv link]

  • Faster Algorithms for Learning Convex Functions
    Ali Siahkamari, Durmus Alp Emre Acar, Christopher Liao, Kelly Geyer, Venkatesh Saligrama, and Brian Kulis
    In Proc. 39th International Conference on Machine Learning, 2022.
    [arxiv link]

  • Convolutional Neural Network Denoising of Focused Ion Beam Micrographs
    Minxu Peng, Mertcan Cokbas, Unay Dorken Gallastegi, Prakash Ishwar, Janusz Konrad, Brian Kulis, and Vivek Goyal
    In IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2021.
    [link coming soon]

  • Tiny-CRNN: Streaming Wakeword Detection in a Low Footprint Setting
    Mohammad Omar Khursheed, Christin Jose, Rajath Kumar, Gengshen Fu, Brian Kulis, and Santosh Kumar Cheekatmalla
    In IEEE AUtomatic Speech Recognition and Understanding (ASRU) Workshop, 2021.
    [arxiv link]

  • Real-Time Localized Photorealistic Video Style Transfer
    Xide Xia, Tianfan Xue, Wei-sheng Lai, Zheng Sun, Abby Chang, Brian Kulis, and Jiawen Chen
    In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021.
    [arxiv link]

  • Learning to Approximate a Bregman Divergence
    Ali Siahkamari, Xide Xia, Venkatesh Saligrama, David Castanon, and Brian Kulis
    In Advances in Neural Information Processing Systems (NeurIPS), 2020.
    [arxiv link]

  • Building a Robust Word-Level Wakeword Verification Network
    Rajath Kumar, Mike Rodehorst, Joe Wang, Jiacheng Gu, and Brian Kulis
    In Proc. 21st INTERSPEECH Conference, 2020.
    [link coming soon]

  • An Audio-Based Wakeword-Independent Verification System
    Joe Wang, Rajath Kumar, Mike Rodehorst, Brian Kulis, and Shiv Vitaladevuni
    In Proc. 21st INTERSPEECH Conference, 2020.
    [link coming soon]

  • Metadata-Aware End-to-End Keyword Spotting
    Hongyi Liu, Apurva Abhyankar, Yuriy Mishchenko, Thibaud Senechal, Gengshen Fu, Brian Kulis, Noah Stein, Anish Shah, and Shiv Vitaladevuni
    In Proc. 21st INTERSPEECH Conference, 2020.
    [link coming soon]

  • Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer
    Xide Xia, Meng Zhang, Tianfan Xue, Zheng Sun, Hui Fang, Brian Kulis, & Jiawen Chen
    In Proc. 16th European Conference on Computer Vision (ECCV), 2020.
    [arxiv link]

  • Deep Divergence Learning
    Kubra Cilingir, Rachel Manzelli, & Brian Kulis
    In Proc. 37th International Conference on Machine Learning (ICML), 2020.
    [arxiv link]

  • Piecewise Linear Regression via a Difference of Convex Functions
    Ali Siahkamari, Aditya Gangrade, Brian Kulis, & Venktaesh Saligrama
    In Proc. 37th International Conference on Machine Learning (ICML), 2020.
    [arxiv link]

  • Learning Bregman Divergences
    Ali Siahkamari, Venktaesh Saligrama, David Castanon, & Brian Kulis
    Arxiv: 1905.11545, 2019.
    [arxiv link]

  • Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses
    Xiao Wang, Siyue Wang, Pin-Yu Chen, Yanzhi Wang, Brian Kulis, Xue Lin, & Peter Chin
    In Proc. 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019.
    [pdf]

  • Deep Metric Learning to Rank
    Kun He, Fatih Cakir, Xide Xia, Brian Kulis, & Stan Sclaroff
    In Proc.Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
    [pdf]

  • Dynamic Clustering Algorithms via Small-Variance Analysis of Markov Chain Mixture Models
    Trevor Campbell, Brian Kulis, & Jonathan How
    IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 41, Number 6, pp. 1338--1352, 2019.
    [arxiv link]

  • Conditioning Deep Generative Raw Audio Models for Structured Automatic Music
    Rachel Manzelli, Vijay Thakkar, Ali Siahkamari, & Brian Kulis
    In Proc. 19th International Society for Music Information Retrieval (ISMIR), 2018.
    [pdf]

  • Inferring Human Traits from Facebook Statuses
    Andrew Cutler & Brian Kulis
    In Proc. 10th International Conference on Social Informatics (SocInfo), 2018.
    [arxiv link]

  • W-Net: A Deep Model for Fully Unsupervised Image Segmentation
    Xide Xia and Brian Kulis
    Arxiv: 1711.08506, 2017.
    [arxiv link]

  • Stable Distribution Alignment using the Dual of the Adversarial Distance
    Ben Usman, Kate Saenko, and Brian Kulis
    Arxiv: 1707.04046, 2017.
    [arxiv link]

  • Combinatorial Topic Models using Small-Variance Asymptotics
    Ke Jiang, Suvrit Sra, & Brian Kulis
    In Proc. 20th Intl. AISTATS Conference, 2017.
    [pdf] [Supplementary Material]

  • Robust Monte Carlo Sampling using Riemannian Nose-Poincare Hamiltonian Dynamics
    Anirban Roychowdhury, Brian Kulis, & Srini Parthasarathy
    In Proc. 33rd International Conference on Machine Learning (ICML), 2016.
    [pdf]

  • Combinatorial Topic Models using Small-Variance Asymptotics
    Ke Jiang, Suvrit Sra, & Brian Kulis
    Arxiv: 1604:02027, 2016.
    [arxiv link]

  • A Sufficient Statistics Construction of Bayesian Nonparametric Exponential Family Conjugate Models
    Robert Finn & Brian Kulis
    Arxiv: 1601.02257, 2016. (Follow-up to the AISTATS paper, with full proofs and further results on conjugacy.)
    [arxiv link]

  • Revisiting Kernelized Locality-Sensitive Hashing for Improved Large-Scale Image Retrieval
    Ke Jiang, Qicaho Que & Brian Kulis
    In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
    [pdf]
    See arXiv version for full proofs: [arxiv link]

  • A Sufficient Statistics Construction of Exponential Family Levy Measure Densities for Nonparametric Conjugate Models
    Robert Finn & Brian Kulis
    In Proc. 18th Intl. AISTATS Conference, 2015.
    [pdf] [Supplementary Material]

  • Power-Law Graph Cuts
    Xiangyang Zhou, Jiaxin Zhang & Brian Kulis
    In Proc. 18th Intl. AISTATS Conference, 2015.
    [pdf]
    Earlier version presented at the NIPS 2014 Workshop on Networks: From Graphs to Rich Data.

  • Gamma Processes, Stick-Breaking, and Variational Inference
    Anirban Roychowdhury & Brian Kulis
    In Proc. 18th Intl. AISTATS Conference, 2015.
    [pdf] [Supplementary Material]
    Earlier version presented at the NIPS 2014 Workshop on Advances in Variational Inference.

  • Asymmetric and Category Invariant Feature Transformations for Domain Adaptation
    Judy Hoffman, Erik Rodner, Jeff Donahue, Brian Kulis, & Kate Saenko
    International Journal of Computer Vision (IJCV), Vol. 109, Numbers 1-2, pp. 28-41, 2014.
    [pdf]

  • Small-Variance Asymptotics for Hidden Markov Models
    Anirban Roychowdhury, Ke Jiang, & Brian Kulis
    In Neural Information Processing Systems (NIPS), 2013.
    [pdf]

  • Dynamic Clustering via Asymptotics of the Dependent Dirichlet Process
    Trevor Campbell, Miao Liu, Brian Kulis, Jonathan How, & Lawrence Carin
    In Neural Information Processing Systems (NIPS), 2013.
    [pdf]

  • MAD-Bayes: MAP-based Asymptotic Derivations from Bayes
    Tamara Broderick, Brian Kulis, & Michael I. Jordan
    In Proc. 30th International Conference on Machine Learning (ICML), 2013.
    [pdf] [Supplementary Material]

  • Metric Learning: A Survey
    Brian Kulis
    Foundations and Trends in Machine Learning, Vol. 5, Number 4, pp. 287--364, 2012.
    [pdf]

  • MAD-Bayes: MAP-based Asymptotic Derivations from Bayes
    Tamara Broderick, Brian Kulis, & Michael I. Jordan
    Arxiv: 1212.2126, 2012.
    [arxiv link]

  • Small-Variance Asymptotics for Exponential Family Dirichlet Process Mixture Models
    Ke Jiang, Brian Kulis, & Michael I. Jordan
    In Neural Information Processing Systems (NIPS), 2012.
    [pdf]

  • Discovering Latent Domains for Multisource Domain Adaptation
    Judy Hoffman, Brian Kulis, Kate Saenko, & Trevor Darrell
    In Proc. 12th European Conference on Computer Vision (ECCV), 2012.
    [pdf] [Supplementary Material]

  • Revisiting k-means: New Algorithms via Bayesian Nonparametrics
    Brian Kulis & Michael I. Jordan
    In Proc. 29th International Conference on Machine Learning (ICML), 2012.
    [pdf]

  • Kernelized Locality-Sensitive Hashing
    Brian Kulis & Kristen Grauman
    IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 6, pp. 1092--1104, 2012.
    [pdf]

  • Metric and Kernel Learning using a Linear Transformation
    Prateek Jain, Brian Kulis, Jason Davis, & Inderjit Dhillon
    Journal of Machine Learning Research, 13 (Mar): 519--547, 2012.
    [pdf]

  • Revisiting k-means: New Algorithms via Bayesian Nonparametrics
    Brian Kulis & Michael I. Jordan
    Arxiv: 1111.0352, 2011.
    [arxiv link]

  • What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms
    Brian Kulis, Kate Saenko & Trevor Darrell
    In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
    Oral Presentation: 3.5% Acceptance Rate
    [pdf]

  • Metric Learning for Reinforcement Learning Agents
    Matthew E. Taylor, Brian Kulis, & Fei Sha
    In 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2011.
    [pdf]

  • Inductive Regularized Learning of Kernel Functions
    Prateek Jain, Brian Kulis, & Inderjit Dhillon
    In Neural Information Processing Systems (NIPS), 2010.
    [pdf]

  • Adapting Visual Category Models to New Domains
    Kate Saenko, Brian Kulis, Mario Fritz & Trevor Darrell
    In Proc. 11th European Conference on Computer Vision (ECCV), 2010.
    [pdf]

  • Implicit Online Learning
    Brian Kulis & Peter Bartlett
    In Proc. 27th International Conference on Machine Learning (ICML), 2010.
    [pdf]

  • Learning to Hash with Binary Reconstructive Embeddings
    Brian Kulis & Trevor Darrell
    In Neural Information Processing Systems (NIPS), 2009.
    [pdf] [code]

  • Learning to Hash with Binary Reconstructive Embeddings
    Brian Kulis & Trevor Darrell
    UC Berkeley EECS Techical Report #UCB/EECS-2009-101, July, 2009.
    [pdf]

  • Fast Similarity Search for Learned Metrics
    Brian Kulis, Prateek Jain, & Kristen Grauman
    IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 12, pp. 2143--2157, 2009.
    [pdf]

  • Kernelized Locality-Sensitive Hashing for Scalable Image Search
    Brian Kulis & Kristen Grauman
    In Proc. 12th International Conference on Computer Vision (ICCV), 2009.
    [pdf] [webpage and code]

  • Convex Perturbations for Scalable Semidefinite Programming
    Brian Kulis, Suvrit Sra, & Inderjit Dhillon
    In Proc. 12th Intl. AISTATS Conference, 2009.
    [pdf]

  • Low-Rank Kernel Learning with Bregman Matrix Divergences
    Brian Kulis, Matyas Sustik, & Inderjit Dhillon
    Journal of Machine Learning Research, 10 (Feb): 341--376, 2009.
    [pdf]

  • Semi-Supervised Graph Clustering: A Kernel Approach
    Brian Kulis, Sugato Basu, Inderjit Dhillon, & Raymond Mooney
    Machine Learning, vol. 74, no. 1, pp. 1--22, 2009.
    [pdf]

  • Online Metric Learning and Fast Similarity Search
    Prateek Jain, Brian Kulis, Inderjit Dhillon, & Kristen Grauman
    In Neural Information Processing Systems (NIPS), 2008.
    Oral Presentation: 2.7% Acceptance Rate
    [pdf], Longer version: [pdf]

  • Fast Image Search for Learned Metrics
    Prateek Jain, Brian Kulis, & Kristen Grauman
    In. Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.
    CVPR 2008 Best Student Paper Award
    [pdf]

  • Fast Similarity Search for Learned Metrics
    Prateek Jain, Brian Kulis, & Kristen Grauman
    UTCS Techical Report #TR-07-48, September 2007.
    [pdf]

  • Scalable Semidefinite Programming using Convex Perturbations
    Brian Kulis, Suvrit Sra, Stefanie Jegelka, & Inderjit Dhillon
    UTCS Technical Report #TR-07-47, September 2007.
    [pdf]

  • Information-Theoretic Metric Learning
    Jason Davis, Brian Kulis, Prateek Jain, Suvrit Sra, & Inderjit Dhillon
    In Proc. 24th International Conference on Machine Learning (ICML), 2007.
    ICML 2007 Best Student Paper Award
    [pdf] [code]

  • Online Linear Regression using Burg Entropy
    Prateek Jain, Brian Kulis, & Inderjit Dhillon
    UTCS Technical Report #TR-07-08, February 2007.
    [pdf]

  • Weighted Graph Cuts without Eigenvectors: A Multilevel Approach
    Inderjit Dhillon, Yuqiang Guan, & Brian Kulis
    IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 11, pp. 1944--1957, 2007.
    [pdf] [code]

  • Fast Low-Rank Semidefinite Programming for Embedding and Clustering
    Brian Kulis, Arun Surendran, & John Platt
    In Proc. 11th Intl. AISTATS Conference, 2007.
    [pdf]

  • Information-Theoretic Metric Learning
    Jason Davis, Brian Kulis, Suvrit Sra, & Inderjit Dhillon
    In NIPS 2006 Workshop on Learning to Compare Examples, 2006.
    [pdf]

  • Learning Low-Rank Kernel Matrices
    Brian Kulis, Matyas Sustik, & Inderjit Dhillon
    In Proc. 23rd International Conference on Machine Learning (ICML), 2006.
    [pdf]

  • A Fast Kernel-Based Multilevel Algorithm for Graph Clustering
    Inderjit Dhillon, Yuqiang Guan, & Brian Kulis
    In Proc. 11th ACM SIGKDD Intl. Conference on Knowledge Discovery and Data Mining, 2005.
    [pdf] [code]

  • Semi-Supervised Graph Clustering: A Kernel Approach
    Brian Kulis, Sugato Basu, Inderjit Dhillon, & Raymond Mooney
    In Proc. 22nd International Conference on Machine Learning (ICML), 2005.
    ICML 2005 Best Student Paper Award
    [pdf]

  • A Unified View of Kernel k-means, Spectral Clustering and Graph Cuts
    Inderjit Dhillon, Yuqiang Guan, & Brian Kulis
    UTCS Technical Report #TR-04-25, July 2004.
    [pdf]

  • Kernel k-means, Spectral Clustering, and Normalized Cuts
    Inderjit Dhillon, Yuqiang Guan, & Brian Kulis
    In Proc. 10th ACM SIGKDD Intl. Conf. on Knowledge Discovery and Data Mining, 2004.
    [pdf]

  • Tracking Evolving Communities in Large Linked Networks
    John Hopcroft, Omar Khan, Brian Kulis, & Bart Selman
    Proc. of the National Academy of Sciences, vol. 101, pp. 5249--5253, April 2004.
    [pdf]

  • Natural Communities in Large Linked Networks
    John Hopcroft, Omar Khan, Brian Kulis, & Bart Selman
    In Proc. 9th ACM SIGKDD Intl. Conf. on Knowledge Discovery and Data Mining, 2003.
    [pdf]