default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDAndrej Risteski
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2025
[i57]Edoardo Botta, Yuchen Li, Aashay Mehta, Jordan T. Ash, Cyril Zhang, Andrej Risteski:
On the Query Complexity of Verifier-Assisted Language Generation. CoRR abs/2502.12123 (2025)- 2024
- [c47]Yilong Qin, Andrej Risteski:
Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Diffusions. COLT 2024: 4413-4457 - [c46]Elan Rosenfeld, Andrej Risteski:
Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization. ICLR 2024 - [c45]Runtian Zhai, Bingbin Liu, Andrej Risteski, J. Zico Kolter, Pradeep Kumar Ravikumar:
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression. ICLR 2024 - [c44]Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta, Yilong Qin, Boris Dadachev, Kishore Papineni, Sanjiv Kumar, Andrej Risteski:
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines. ICML 2024 - [i56]Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta, Yilong Qin, Boris Dadachev, Kishore Papineni, Sanjiv Kumar, Andrej Risteski:
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines. CoRR abs/2407.21046 (2024) - [i55]Ricardo Buitrago Ruiz, Tanya Marwah, Albert Gu, Andrej Risteski:
On the Benefits of Memory for Modeling Time-Dependent PDEs. CoRR abs/2409.02313 (2024) - [i54]Abhishek Panigrahi, Bingbin Liu, Sadhika Malladi, Andrej Risteski, Surbhi Goel:
Progressive distillation induces an implicit curriculum. CoRR abs/2410.05464 (2024) - [i53]Dhruv Rohatgi, Tanya Marwah, Zachary Chase Lipton, Jianfeng Lu, Ankur Moitra, Andrej Risteski:
Towards characterizing the value of edge embeddings in Graph Neural Networks. CoRR abs/2410.09867 (2024) - 2023
- [c43]Frederic Koehler, Alexander Heckett, Andrej Risteski:
Statistical Efficiency of Score Matching: The View from Isoperimetry. ICLR 2023 - [c42]Holden Lee, Chirag Pabbaraju, Anish Prasad Sevekari, Andrej Risteski:
Pitfalls of Gaussians as a noise distribution in NCE. ICLR 2023 - [c41]Yuchen Li, Yuanzhi Li, Andrej Risteski:
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding. ICML 2023: 19689-19729 - [c40]Tanya Marwah, Zachary Chase Lipton, Jianfeng Lu, Andrej Risteski:
Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective. ICML 2023: 24139-24172 - [c39]Omar Chehab, Aapo Hyvärinen, Andrej Risteski:
Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond. NeurIPS 2023 - [c38]Tanya Marwah, Ashwini Pokle, J. Zico Kolter, Zachary C. Lipton, Jianfeng Lu, Andrej Risteski:
Deep Equilibrium Based Neural Operators for Steady-State PDEs. NeurIPS 2023 - [c37]Chirag Pabbaraju, Dhruv Rohatgi, Anish Prasad Sevekari, Holden Lee, Ankur Moitra, Andrej Risteski:
Provable benefits of score matching. NeurIPS 2023 - [c36]Kaiyue Wen, Yuchen Li, Bingbin Liu, Andrej Risteski:
Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars. NeurIPS 2023 - [i52]Yuchen Li, Yuanzhi Li, Andrej Risteski:
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding. CoRR abs/2303.04245 (2023) - [i51]Runtian Zhai, Bingbin Liu, Andrej Risteski, Zico Kolter, Pradeep Ravikumar:
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation. CoRR abs/2306.00788 (2023) - [i50]Chirag Pabbaraju, Dhruv Rohatgi, Anish Prasad Sevekari, Holden Lee, Ankur Moitra, Andrej Risteski:
Provable benefits of score matching. CoRR abs/2306.01993 (2023) - [i49]Yilong Qin, Andrej Risteski:
Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Markov Chains. CoRR abs/2306.09332 (2023) - [i48]Omar Chehab
, Aapo Hyvärinen, Andrej Risteski:
Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond. CoRR abs/2310.03902 (2023) - [i47]Elan Rosenfeld, Andrej Risteski:
Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization. CoRR abs/2311.04163 (2023) - [i46]Tanya Marwah, Ashwini Pokle, J. Zico Kolter, Zachary C. Lipton, Jianfeng Lu, Andrej Risteski:
Deep Equilibrium Based Neural Operators for Steady-State PDEs. CoRR abs/2312.00234 (2023) - [i45]Kaiyue Wen, Yuchen Li, Bingbin Liu, Andrej Risteski:
Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars. CoRR abs/2312.01429 (2023) - 2022
- [c35]Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski:
An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization. AISTATS 2022: 2641-2657 - [c34]Ashwini Pokle, Jinjin Tian, Yuchen Li, Andrej Risteski:
Contrasting the landscape of contrastive and non-contrastive learning. AISTATS 2022: 8592-8618 - [c33]Frederic Koehler, Holden Lee, Andrej Risteski:
Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods. COLT 2022: 4945-4988 - [c32]Frederic Koehler, Viraj Mehta, Chenghui Zhou, Andrej Risteski:
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias. ICLR 2022 - [c31]Bingbin Liu, Elan Rosenfeld, Pradeep Kumar Ravikumar, Andrej Risteski:
Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation. ICLR 2022 - [c30]Divyansh Pareek, Andrej Risteski:
The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders. ICLR 2022 - [c29]Yining Chen, Elan Rosenfeld, Mark Sellke, Tengyu Ma, Andrej Risteski:
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments. NeurIPS 2022 - [c28]Bingbin Liu, Daniel J. Hsu, Pradeep Ravikumar, Andrej Risteski:
Masked Prediction: A Parameter Identifiability View. NeurIPS 2022 - [c27]Binghui Peng, Andrej Risteski:
Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions. NeurIPS 2022 - [i44]Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski:
Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization. CoRR abs/2202.06856 (2022) - [i43]Frederic Koehler, Holden Lee, Andrej Risteski:
Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods. CoRR abs/2202.08907 (2022) - [i42]Bingbin Liu, Daniel Hsu, Pradeep Ravikumar, Andrej Risteski:
Masked prediction tasks: a parameter identifiability view. CoRR abs/2202.09305 (2022) - [i41]Binghui Peng, Andrej Risteski:
Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions. CoRR abs/2203.14383 (2022) - [i40]Ashwini Pokle, Jinjin Tian, Yuchen Li, Andrej Risteski:
Contrasting the landscape of contrastive and non-contrastive learning. CoRR abs/2203.15702 (2022) - [i39]Holden Lee, Chirag Pabbaraju, Anish Prasad Sevekari, Andrej Risteski:
Pitfalls of Gaussians as a noise distribution in NCE. CoRR abs/2210.00189 (2022) - [i38]Frederic Koehler, Alexander Heckett, Andrej Risteski:
Statistical Efficiency of Score Matching: The View from Isoperimetry. CoRR abs/2210.00726 (2022) - [i37]Tanya Marwah, Zachary C. Lipton, Jianfeng Lu, Andrej Risteski:
Neural Network Approximations of PDEs Beyond Linearity: Representational Perspective. CoRR abs/2210.12101 (2022) - 2021
- [c26]Yuchen Li, Andrej Risteski:
The Limitations of Limited Context for Constituency Parsing. ACL/IJCNLP (1) 2021: 2675-2687 - [c25]Bingbin Liu, Pradeep Ravikumar, Andrej Risteski:
Contrastive learning of strong-mixing continuous-time stochastic processes. AISTATS 2021: 3151-3159 - [c24]Rong Ge, Holden Lee, Jianfeng Lu, Andrej Risteski:
Efficient sampling from the Bingham distribution. ALT 2021: 673-685 - [c23]Elan Rosenfeld, Pradeep Kumar Ravikumar, Andrej Risteski:
The Risks of Invariant Risk Minimization. ICLR 2021 - [c22]Frederic Koehler, Viraj Mehta, Andrej Risteski:
Representational aspects of depth and conditioning in normalizing flows. ICML 2021: 5628-5636 - [c21]Holden Lee, Chirag Pabbaraju, Anish Prasad Sevekari, Andrej Risteski:
Universal Approximation Using Well-Conditioned Normalizing Flows. NeurIPS 2021: 12700-12711 - [c20]Tanya Marwah, Zachary C. Lipton, Andrej Risteski:
Parametric Complexity Bounds for Approximating PDEs with Neural Networks. NeurIPS 2021: 15044-15055 - [i36]Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski:
An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization. CoRR abs/2102.13128 (2021) - [i35]Tanya Marwah, Zachary C. Lipton, Andrej Risteski:
Parametric Complexity Bounds for Approximating PDEs with Neural Networks. CoRR abs/2103.02138 (2021) - [i34]Bingbin Liu, Pradeep Ravikumar, Andrej Risteski:
Contrastive learning of strong-mixing continuous-time stochastic processes. CoRR abs/2103.02740 (2021) - [i33]Yuchen Li, Andrej Risteski:
The Limitations of Limited Context for Constituency Parsing. CoRR abs/2106.01580 (2021) - [i32]Yining Chen, Elan Rosenfeld, Mark Sellke, Tengyu Ma, Andrej Risteski:
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments. CoRR abs/2106.09913 (2021) - [i31]Holden Lee, Chirag Pabbaraju, Anish Prasad Sevekari, Andrej Risteski:
Universal Approximation for Log-concave Distributions using Well-conditioned Normalizing Flows. CoRR abs/2107.02951 (2021) - [i30]Divyansh Pareek, Andrej Risteski:
The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders. CoRR abs/2107.04652 (2021) - [i29]Bingbin Liu, Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski:
Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation. CoRR abs/2110.11271 (2021) - [i28]Frederic Koehler, Viraj Mehta, Andrej Risteski, Chenghui Zhou:
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias. CoRR abs/2112.06868 (2021) - 2020
- [c19]Rares-Darius Buhai, Yoni Halpern, Yoon Kim, Andrej Risteski, David A. Sontag:
Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models. ICML 2020: 1211-1219 - [c18]Han Zhao, Junjie Hu, Andrej Risteski:
On Learning Language-Invariant Representations for Universal Machine Translation. ICML 2020: 11352-11364 - [i27]Ankur Moitra, Andrej Risteski:
Fast Convergence for Langevin Diffusion with Matrix Manifold Structure. CoRR abs/2002.05576 (2020) - [i26]Han Zhao, Junjie Hu, Andrej Risteski:
On Learning Language-Invariant Representations for Universal Machine Translation. CoRR abs/2008.04510 (2020) - [i25]Rong Ge, Holden Lee, Jianfeng Lu, Andrej Risteski:
Efficient sampling from the Bingham distribution. CoRR abs/2010.00137 (2020) - [i24]Frederic Koehler, Viraj Mehta, Andrej Risteski:
Representational aspects of depth and conditioning in normalizing flows. CoRR abs/2010.01155 (2020) - [i23]Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski:
The Risks of Invariant Risk Minimization. CoRR abs/2010.05761 (2020)
2010 – 2019
- 2019
- [c17]Dylan J. Foster, Andrej Risteski:
Sum-of-squares meets square loss: Fast rates for agnostic tensor completion. COLT 2019: 1280-1318 - [c16]Yu Bai, Tengyu Ma, Andrej Risteski:
Approximability of Discriminators Implies Diversity in GANs. ICLR (Poster) 2019 - [c15]Frederic Koehler, Andrej Risteski:
The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent Structure. ICLR (Poster) 2019 - [c14]Vishesh Jain, Frederic Koehler, Andrej Risteski:
Mean-field approximation, convex hierarchies, and the optimality of correlation rounding: a unified perspective. STOC 2019: 1226-1236 - [i22]Dylan J. Foster, Andrej Risteski:
Sum-of-squares meets square loss: Fast rates for agnostic tensor completion. CoRR abs/1905.13283 (2019) - [i21]Rares-Darius Buhai, Andrej Risteski, Yoni Halpern, David A. Sontag:
Benefits of Overparameterization in Single-Layer Latent Variable Generative Models. CoRR abs/1907.00030 (2019) - 2018
- [j3]Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski:
Linear Algebraic Structure of Word Senses, with Applications to Polysemy. Trans. Assoc. Comput. Linguistics 6: 483-495 (2018) - [c13]Sanjeev Arora, Andrej Risteski, Yi Zhang:
Do GANs learn the distribution? Some Theory and Empirics. ICLR (Poster) 2018 - [c12]Holden Lee, Andrej Risteski, Rong Ge:
Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo. NeurIPS 2018: 7858-7867 - [i20]Frederic Koehler, Andrej Risteski:
Representational Power of ReLU Networks and Polynomial Kernels: Beyond Worst-Case Analysis. CoRR abs/1805.11405 (2018) - [i19]Yu Bai, Tengyu Ma, Andrej Risteski:
Approximability of Discriminators Implies Diversity in GANs. CoRR abs/1806.10586 (2018) - [i18]Vishesh Jain, Frederic Koehler, Andrej Risteski:
Mean-field approximation, convex hierarchies, and the optimality of correlation rounding: a unified perspective. CoRR abs/1808.07226 (2018) - [i17]Rong Ge, Holden Lee, Andrej Risteski:
Simulated Tempering Langevin Monte Carlo II: An Improved Proof using Soft Markov Chain Decomposition. CoRR abs/1812.00793 (2018) - 2017
- [b1]Andrej Risteski:
New Techniques for Learning and Inference in Bayesian Models. Princeton University, USA, 2017 - [c11]Holden Lee, Rong Ge, Tengyu Ma, Andrej Risteski, Sanjeev Arora:
On the Ability of Neural Nets to Express Distributions. COLT 2017: 1271-1296 - [c10]Sanjeev Arora, Rong Ge, Tengyu Ma, Andrej Risteski:
Provable learning of noisy-OR networks. STOC 2017: 1057-1066 - [i16]Holden Lee, Rong Ge, Andrej Risteski, Tengyu Ma, Sanjeev Arora:
On the ability of neural nets to express distributions. CoRR abs/1702.07028 (2017) - [i15]Mikhail Khodak, Andrej Risteski, Christiane Fellbaum, Sanjeev Arora:
Extending and Improving Wordnet via Unsupervised Word Embeddings. CoRR abs/1705.00217 (2017) - [i14]Sanjeev Arora, Andrej Risteski:
Provable benefits of representation learning. CoRR abs/1706.04601 (2017) - [i13]Rong Ge, Holden Lee, Andrej Risteski:
Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo. CoRR abs/1710.02736 (2017) - [i12]Sanjeev Arora, Andrej Risteski, Yi Zhang:
Theoretical limitations of Encoder-Decoder GAN architectures. CoRR abs/1711.02651 (2017) - 2016
- [j2]Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski:
A Latent Variable Model Approach to PMI-based Word Embeddings. Trans. Assoc. Comput. Linguistics 4: 385-399 (2016) - [c9]Andrej Risteski:
How to calculate partition functions using convex programming hierarchies: provable bounds for variational methods. COLT 2016: 1402-1416 - [c8]Yuanzhi Li, Yingyu Liang, Andrej Risteski:
Recovery guarantee of weighted low-rank approximation via alternating minimization. ICML 2016: 2358-2367 - [c7]Andrej Risteski, Yuanzhi Li:
Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods. NIPS 2016: 4628-4636 - [c6]Andrej Risteski, Yuanzhi Li:
Algorithms and matching lower bounds for approximately-convex optimization. NIPS 2016: 4745-4753 - [c5]Yuanzhi Li, Yingyu Liang, Andrej Risteski:
Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates. NIPS 2016: 4988-4996 - [c4]Alina Ene, Matthias Mnich, Marcin Pilipczuk, Andrej Risteski:
On Routing Disjoint Paths in Bounded Treewidth Graphs. SWAT 2016: 15:1-15:15 - [i11]Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski:
Linear Algebraic Structure of Word Senses, with Applications to Polysemy. CoRR abs/1601.03764 (2016) - [i10]Yuanzhi Li, Yingyu Liang, Andrej Risteski:
Recovery guarantee of weighted low-rank approximation via alternating minimization. CoRR abs/1602.02262 (2016) - [i9]Andrej Risteski:
How to calculate partition functions using convex programming hierarchies: provable bounds for variational methods. CoRR abs/1607.03183 (2016) - [i8]Yuanzhi Li, Andrej Risteski:
Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods. CoRR abs/1607.03360 (2016) - [i7]Yuanzhi Li, Yingyu Liang, Andrej Risteski:
Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates. CoRR abs/1611.03819 (2016) - [i6]Sanjeev Arora, Rong Ge, Tengyu Ma, Andrej Risteski:
Provable learning of Noisy-or Networks. CoRR abs/1612.08795 (2016) - 2015
- [c3]Pranjal Awasthi, Moses Charikar, Kevin A. Lai, Andrej Risteski:
Label optimal regret bounds for online local learning. COLT 2015: 150-166 - [c2]Pranjal Awasthi, Andrej Risteski:
On some provably correct cases of variational inference for topic models. NIPS 2015: 2098-2106 - [i5]Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski:
Random Walks on Context Spaces: Towards an Explanation of the Mysteries of Semantic Word Embeddings. CoRR abs/1502.03520 (2015) - [i4]Pranjal Awasthi, Moses Charikar, Kevin A. Lai, Andrej Risteski:
Label optimal regret bounds for online local learning. CoRR abs/1503.02193 (2015) - [i3]Pranjal Awasthi, Andrej Risteski:
On some provably correct cases of variational inference for topic models. CoRR abs/1503.06567 (2015) - [i2]Alina Ene, Matthias Mnich, Marcin Pilipczuk, Andrej Risteski:
On Routing Disjoint Paths in Bounded Treewidth Graphs. CoRR abs/1512.01829 (2015) - 2014
- [j1]Howard Cheng, Satyan L. Devadoss, Brian Li, Andrej Risteski:
Skeletal configurations of ribbon trees. Discret. Appl. Math. 170: 46-54 (2014) - 2012
- [c1]Oswin Aichholzer, Howard Cheng, Satyan L. Devadoss, Thomas Hackl, Stefan Huber, Brian Li, Andrej Risteski:
What makes a Tree a Straight Skeleton? CCCG 2012: 253-258 - [i1]Howard Cheng, Satyan L. Devadoss, Brian Li, Andrej Risteski:
Skeletal Rigidity of Phylogenetic Trees. CoRR abs/1203.5782 (2012)
Coauthor Index
Pradeep Ravikumar
aka: Pradeep Kumar Ravikumar
aka: Pradeep Kumar Ravikumar
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-03-21 02:17 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
