VV
Victor Veitch
cs.LGstat.MLcs.CLcs.AIcs.SIstat.MEmath.COmath.STquant-phstat.TH
On Valency
published · living versionsW_tmkdk2up·v1 · currentpublished
The Resource Theory of Stabilizer Computation
with Seyed Ali Hamed Mousavian, Daniel Gottesman, Joseph Emerson
1 version
Preprints & journals
44 papers in the corpus · 2013–2026Can LLMs Anticipate Their Cruxes?2610.21006v1 · David Reber, James Reber, Ari Holtzman et al.2026 · 0 citationsarXiv
Anchor Divergence for Semantic Geometry in Contrastive Learning2610.06919v1 · Akash Kannan, Kiho Park, Victor Veitch2026 · 0 citationsarXiv
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms2606.30625v1 · Ziwei Su, Junyu Ren, Victor Veitch2026 · 0 citationsarXiv
Expected Reward Prediction, with Applications to Model Routing2603.20217v1 · Kenan Hasanaliyev, Silas Alberti, Jenny Hamer et al.2026 · 0 citationsarXiv
The Information Geometry of Softmax: Probing and Steering2602.15293v2 · Kiho Park, Todd Nief, Yo Joong Choe et al.2026 · 0 citationsIn Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026
Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning2510.05251v1 · Chenghao Yang, Lin Gui, Chenxiao Yang et al.2025 · 0 citationsarXiv
Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training2509.21500v3 · Junkai Zhang, Zihao Wang, Lin Gui et al.2025 · 0 citationsarXiv
Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures2506.01197v1 · Mark Muchane, Sean Richardson, Kiho Park et al.2025 · 0 citationsarXiv
Does Editing Provide Evidence for Localization?2502.11447v2 · Zihao Wang, Victor Veitch2025 · 0 citationsarXiv
RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals2410.11348v3 · David Reber, Sean Richardson, Todd Nief et al.2024 · 0 citationsarXiv
The Geometry of Categorical and Hierarchical Concepts in Large Language Models2406.01506v3 · Kiho Park, Yo Joong Choe, Yibo Jiang et al.2024 · 3 citationsarXiv
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling2406.00832v3 · Lin Gui, Cristina Garbacea, Victor Veitch2024 · 3 citationsarXiv
On the Origins of Linear Representations in Large Language Models2403.03867v1 · Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar et al.2024 · 2 citationsarXiv
Transforming and Combining Rewards for Aligning Large Language Models2402.00742v2 · Zihao Wang, Chirag Nagpal, Jonathan Berant et al.2024 · 1 citationarXiv
The Linear Representation Hypothesis and the Geometry of Large Language Models2311.03658v2 · Kiho Park, Yo Joong Choe, Victor Veitch2023 · 11 citationsIn Proceedings of the 41st International Conference on Machine Learning (ICML), 2024
Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness2310.19691v1 · Jacy Reese Anthis, Victor Veitch2023 · 4 citationsarXiv
Uncovering Meanings of Embeddings via Partial Orthogonality2310.17611v1 · Yibo Jiang, Bryon Aragam, Victor Veitch2023 · 0 citationsarXiv
Concept Algebra for (Score-Based) Text-Controlled Generative Models2302.03693v6 · Zihao Wang, Lin Gui, Jeffrey Negrea et al.2023 · 8 citationsarXiv
Efficient Conditionally Invariant Representation Learning2212.08645v2 · Roman Pogodin, Namrata Deka, Yazhe Li et al.2022 · 3 citationsThe Eleventh International Conference on Learning Representations, 2023
Causal Estimation for Text Data with (Apparent) Overlap Violations2210.00079v3 · Lin Gui, Victor Veitch2022 · 6 citationsarXiv
The Causal Structure of Domain Invariant Supervised Representation Learning2208.06987v4 · Zihao Wang, Victor Veitch2022 · 2 citationsarXiv
Invariant and Transportable Representations for Anti-Causal Domain Shifts2207.01603v1 · Yibo Jiang, Victor Veitch2022 · 7 citationsarXiv
Using Embeddings for Causal Estimation of Peer Influence in Social Networks2205.08033v1 · Irina Cristali, Victor Veitch2022 · 7 citationsarXiv
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond2109.00725v2 · Amir Feder, Katherine A. Keith, Emaad Manzoor et al.2021 · 206 citationsarXiv
Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests2106.00545v3 · Victor Veitch, Alexander D'Amour, Steve Yadlowsky et al.2021 · 19 citationsarXiv
Invariant Representation Learning for Treatment Effect Estimation2011.12379v2 · Claudia Shi, Victor Veitch, David Blei2020 · 12 citationsarXiv
Underspecification Presents Challenges for Credibility in Modern Machine Learning2011.03395v2 · Alexander D'Amour, Katherine Heller, Dan Moldovan et al.2020 · 398 citationsarXiv
Causal Effects of Linguistic Properties2010.12919v5 · Reid Pryzant, Dallas Card, Dan Jurafsky et al.2020 · 32 citationsarXiv
Valid Causal Inference with (Some) Invalid Instruments2006.11386v1 · Jason Hartford, Victor Veitch, Dhanya Sridhar et al.2020 · 12 citationsarXiv
Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding2003.01747v2 · Victor Veitch, Anisha Zaveri2020 · 24 citationsarXiv
Adapting Neural Networks for the Estimation of Treatment Effects1906.02120v2 · Claudia Shi, David M. Blei, Victor Veitch2019 · 163 citationsarXiv
Adapting Text Embeddings for Causal Inference1905.12741v2 · Victor Veitch, Dhanya Sridhar, David M. Blei2019 · 71 citationsarXiv
Using Embeddings to Correct for Unobserved Confounding in Networks1902.04114v2 · Victor Veitch, Yixin Wang, David M. Blei2019 · 26 citationsarXiv
The Holdout Randomization Test for Feature Selection in Black Box Models1811.00645v4 · Wesley Tansey, Victor Veitch, Haoran Zhang et al.2018 · 22 citationsarXiv
Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data1806.10701v2 · Victor Veitch, Morgane Austern, Wenda Zhou et al.2018 · 4 citationsarXiv
Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach1804.05862v3 · Wenda Zhou, Victor Veitch, Morgane Austern et al.2018 · 89 citationsarXiv
Exchangeable modelling of relational data: checking sparsity, train-test splitting, and sparse exchangeable Poisson matrix factorization1712.02311v1 · Victor Veitch, Ekansh Sharma, Zacharie Naulet et al.2017 · 0 citationsarXiv
Bootstrap estimators for the tail-index and for the count statistics of graphex processes1712.01745v3 · Zacharie Naulet, Daniel M. Roy, Ekansh Sharma et al.2017 · 9 citationsarXiv
Sampling perspectives on sparse exchangeable graphs1708.03237v2 · Christian Borgs, Jennifer T. Chayes, Henry Cohn et al.2017 · 23 citationsAnnals of Probability 47 (2019), no. 5, 2754-2800
Sampling and Estimation for (Sparse) Exchangeable Graphs1611.00843v1 · Victor Veitch, Daniel M. Roy2016 · 36 citationsarXiv
The Class of Random Graphs Arising from Exchangeable Random Measures1512.03099v1 · Victor Veitch, Daniel M. Roy2015 · 67 citationsarXiv
Contextuality supplies the 'magic' for quantum computation.24919152 · Howard, Mark, Wallman, Joel, Veitch, Victor et al.2014 · 619 citationsNature. 2014;510(7505):351-5
The whole is greater than the sum of the parts: on the possibility of purely statistical interpretations of quantum theory1312.1345v1 · Joseph Emerson, Dmitry Serbin, Chris Sutherland et al.2013 · 17 citationsarXiv
The Resource Theory of Stabilizer Computation1307.7171v1 · Victor Veitch, Seyed Ali Hamed Mousavian, Daniel Gottesman et al.2013 · 505 citationsNew J. Phys. 16 (2014) 013009on Valency
Career total: 62 works. 44 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.