Shane Bergsma - RankMe

52 papers A* 15A 1B 7Misc 1Journal 12Unranked 15

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Don't be lazy: CompleteP enables compute-efficient deep transformers. CoRR Nolan Dey, Bin Claire Zhang, Lorenzo Noci, Mufan Bill Li, Blake Bordelon, Shane Bergsma, Cengiz Pehlevan, Boris Hanin, Joel Hestness
2025	J	`jnl`	PTPP-Aware Adaptation Scaling Laws: Predicting Domain-Adaptation Performance at Unseen Pre-Training Budgets. CoRR Étienne Goffinet, Shane Bergsma, Avraham Sheinin, Natalia Vassilieva, Shaheer Muhammad, Preslav Nakov, Gurpreet Gosal
2025	J	`jnl`	Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training. CoRR Shane Bergsma, Nolan Dey, Gurpreet Gosal, Gavia Gray, Daria Soboleva, Joel Hestness
2025	J	`jnl`	Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs. CoRR Shane Bergsma, Nolan Dey, Joel Hestness
2025	J	`jnl`	Scaling with Collapse: Efficient and Predictable Training of LLM Families. CoRR Shane Bergsma, Bin Claire Zhang, Nolan Dey, Shaheer Muhammad, Gurpreet Gosal, Joel Hestness
2025	A*	`conf`	Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs. ICLR Shane Bergsma, Nolan Simran Dey, Gurpreet Gosal, Gavia Gray, Daria Soboleva, Joel Hestness
2025	J	`jnl`	Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs. CoRR Shane Bergsma, Nolan Dey, Gurpreet Gosal, Gavia Gray, Daria Soboleva, Joel Hestness
2024	A*	`conf`	Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers. NeurIPS Gavia Gray, Aman Tiwari, Shane Bergsma, Joel Hestness
2024	J	`jnl`	Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers. CoRR Gavia Gray, Aman Tiwari, Shane Bergsma, Joel Hestness
2024	A*	`conf`	Sparse maximal update parameterization: A holistic approach to sparse training dynamics. NeurIPS Nolan Dey, Shane Bergsma, Joel Hestness
2024	J	`jnl`	Sparse maximal update parameterization: A holistic approach to sparse training dynamics. CoRR Nolan Dey, Shane Bergsma, Joel Hestness
2023	J	`jnl`	C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting. CoRR Shane Bergsma, Timothy Zeyl, Javad Rahimipour Anaraki, Lei Guo
2023	A*	`conf`	SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting. NeurIPS Shane Bergsma, Timothy Zeyl, Lei Guo
2023	J	`jnl`	SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting. CoRR Shane Bergsma, Timothy Zeyl, Lei Guo
2022	A*	`conf`	C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting. NeurIPS Shane Bergsma, Timothy Zeyl, Javad Rahimipour Anaraki, Lei Guo
2022	—	`conf`	CoSpot: a cooperative VM allocation framework for increased revenue from spot instances. SoCC Syed M. Iqbal, Haley Li, Shane Bergsma, Ivan Beschastnikh, Alan J. Hu
2022	J	`jnl`	Gridiron: A Technique for Augmenting Cloud Workloads with Network Bandwidth Requirements. CoRR Nodir Kodirov, Shane Bergsma, Syed M. Iqbal, Alan J. Hu, Ivan Beschastnikh, Margo I. Seltzer
2021	B	`conf`	Fundy: A Scalable and Extensible Resource Manager for Cloud Resources. CLOUD Xiaodi Ke, Cong Guo, Siqi Ji, Shane Bergsma, Zhenhua Hu, Lei Guo
2021	A*	`conf`	Generating Complex, Realistic Cloud Workloads using Recurrent Neural Networks. SOSP Shane Bergsma, Timothy Zeyl, Arik Senderovich, J. Christopher Beck
2019	A	`conf`	Minimum Makespan Workflow Scheduling for Malleable Jobs with Precedence Constraints and Lifetime Resource Demands. ICDCS Chen Chen, Xiaodi Ke, Timothy Zeyl, Kaixiang Du, Sam Sanjabi, Shane Bergsma, Reza Pournaghi, Chong Chen
2016	—	`ch.`	Extracting Anaphoric Agreement Properties from Corpora. Anaphora Resolution - Algorithms, Resources, and Applications Shane Bergsma
2014	—	`conf`	I'm a Belieber: Social Roles via Self-identification and Conceptual Attributes. ACL (2) Charley Beller, Rebecca Knowles, Craig Harman, Shane Bergsma, Margaret Mitchell, Benjamin Van Durme
2014	—	`conf`	Learning to Measure Influence in a Scientific Social Network. Canadian AI Shane Bergsma, Regan L. Mandryk, Gordon McCalla
2013	—	`conf`	Broadly Improving User Classification via Communication-Based Name and Location Clustering on Twitter. HLT-NAACL Shane Bergsma, Mark Dredze, Benjamin Van Durme, Theresa Wilson, David Yarowsky
2013	—	`conf`	Explicit and Implicit Syntactic Features for Text Classification. ACL (2) Matt Post, Shane Bergsma
2013	J	`jnl`	Learning Domain-Specific, L1-Specific Measures of Word Readability. Trait. Autom. des Langues Shane Bergsma, David Yarowsky
2013	—	`conf`	Using Conceptual Class Attributes to Characterize Social Media Users. ACL (1) Shane Bergsma, Benjamin Van Durme
2012	—	`conf`	Stylometric Analysis of Scientific Articles. HLT-NAACL Shane Bergsma, Matt Post, David Yarowsky
2011	—	`conf`	Joint Training of Dependency Parsing Filters through Latent Support Vector Machines. ACL (2) Colin Cherry, Shane Bergsma
2011	A*	`conf`	Learning Bilingual Lexicons Using the Visual Similarity of Labeled Web Images. IJCAI Shane Bergsma, Benjamin Van Durme
2011	—	`conf`	NADA: A Robust System for Non-referential Pronoun Detection. DAARC Shane Bergsma, David Yarowsky
2011	A*	`conf`	Using Large Monolingual and Bilingual Corpora to Improve Coordination Disambiguation. ACL Shane Bergsma, David Yarowsky, Kenneth Ward Church
2011	Misc	`conf`	Using Visual Information to Predict Lexical Preference. RANLP Shane Bergsma, Randy Goebel
2010	A*	`conf`	Creating Robust Supervised Classifiers via Web-Scale N-Gram Data. ACL Shane Bergsma, Emily Pitler, Dekang Lin
2010	B	`conf`	Fast and Accurate Arc Filtering for Dependency Parsing. COLING Shane Bergsma, Colin Cherry
2010	B	`conf`	Improved Natural Language Learning via Variance-Regularization Support Vector Machines. CoNLL Shane Bergsma, Dekang Lin, Dale Schuurmans
2010	B	`conf`	New Tools for Web-Scale N-grams. LREC Dekang Lin, Kenneth Ward Church, Heng Ji, Satoshi Sekine, David Yarowsky, Shane Bergsma, Kailash Patil, Emily Pitler, Rachel Lathbury, Vikram Rao, Kapil Dalwani, Sushant Narsale
2010	A*	`conf`	Predicting the Semantic Compositionality of Prefix Verbs. EMNLP Shane Bergsma, Aditya Bhargava, Hua He, Grzegorz Kondrak
2010	—	`conf`	The nature of noise in linguistic corpora. AND Randy Goebel, Shane Bergsma, Ying Xu, Christoph Ringlstetter, Mi-Young Kim
2010	—	`conf`	Transliteration Generation and Mining with Limited Training Resources. NEWS@ACL Sittichai Jiampojamarn, Kenneth Dwyer, Shane Bergsma, Aditya Bhargava, Qing Dou, Mi-Young Kim, Grzegorz Kondrak
2010	B	`conf`	Using Web-scale N-grams to Improve Base NP Parsing Performance. COLING Emily Pitler, Shane Bergsma, Dekang Lin, Kenneth Ward Church
2009	—	`conf`	A Ranking Approach to Stress Prediction for Letter-to-Phoneme Conversion. ACL/IJCNLP Qing Dou, Shane Bergsma, Sittichai Jiampojamarn, Grzegorz Kondrak
2009	B	`conf`	Glen, Glenda or Glendale: Unsupervised and Semi-supervised Learning of English Noun Gender. CoNLL Shane Bergsma, Dekang Lin, Randy Goebel
2009	A*	`conf`	Web-Scale N-gram Models for Lexical Disambiguation. IJCAI Shane Bergsma, Dekang Lin, Randy Goebel
2008	A*	`conf`	Discriminative Learning of Selectional Preference from Unlabeled Text. EMNLP Shane Bergsma, Dekang Lin, Randy Goebel
2008	A*	`conf`	Distributional Identification of Non-Referential Pronouns. ACL Shane Bergsma, Dekang Lin, Randy Goebel
2007	A*	`conf`	Alignment-Based Discriminative String Similarity. ACL Shane Bergsma, Grzegorz Kondrak
2007	—	`conf`	Automatic Answer Typing for How-Questions. HLT-NAACL Christopher Pinchak, Shane Bergsma
2007	—	`conf`	Learning Noun Phrase Query Segmentation. EMNLP-CoNLL Shane Bergsma, Qin Iris Wang
2006	A*	`conf`	Bootstrapping Path-Based Pronoun Resolution. ACL Shane Bergsma, Dekang Lin
2005	B	`conf`	An Expectation Maximization Approach to Pronoun Resolution. CoNLL Colin Cherry, Shane Bergsma
2005	—	`conf`	Automatic Acquisition of Gender Information for Anaphora Resolution. Canadian AI Shane Bergsma