← Authors

Andrej Risteski

48 papers · 2015–2025 · 8 conferences · across top CS/AI conferences

Achievements

πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (5) 🧭 Keyword Pioneer πŸ—ΊοΈ Taxonomy Completionist (51) 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (10) 🐣 Hot Topic Early Bird πŸ† Keyword Champion (3) πŸ‘‘ Triple Crown πŸ—ƒοΈ Keyword Collector (142) ⚑ Prolific Year (8) πŸš€ Conference Pioneer πŸ’Ž Century Club (48) πŸ”₯ Unstoppable (11) πŸ“ˆ Trend Setter ❓ The Questioner

Conferences

NIPS (14) ICLR (13) ICML (9) COLT (6) AISTATS (3) ACL (1) ALT (1) IJCNLP (1)

Top co-authors

Yuchen Li (7) Holden Lee (7) Bingbin Liu (6) Elan Rosenfeld (5) Frederic Koehler (5) Tanya Marwah (5) Yuanzhi Li (5) Jianfeng Lu (4) Tengyu Ma (3) Pradeep Kumar Ravikumar (3)

Keywords

variational inference (6) representation learning (4) gradient descent (4) representational power (3) ising model (3) latent variable model (3) neural network (3) partial differential equation (3) partition function (3) online learning (3) generative model (2) domain generalization (2) constituency parsing (2) wasserstein distance (2) exponential family (2) curse of dimensionality (2) markov chain monte carlo (2) self-supervised learning (2) unsupervised learning (2) unsupervised parsing (2)

Papers

Towards characterizing the value of edge embeddings in Graph Neural Networks ICML 2025
Progressive distillation induces an implicit curriculum ICLR 2025
On the Benefits of Memory for Modeling Time-Dependent PDEs ICLR 2025
On the Query Complexity of Verifier-Assisted Language Generation ICML 2025
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression ICLR 2024
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines ICML 2024
Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization ICLR 2024
Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Diffusions COLT 2024
Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond NIPS 2023
Provable benefits of score matching NIPS 2023
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding ICML 2023
Pitfalls of Gaussians as a noise distribution in NCE ICLR 2023
Statistical Efficiency of Score Matching: The View from Isoperimetry ICLR 2023
Deep Equilibrium Based Neural Operators for Steady-State PDEs NIPS 2023
Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective ICML 2023
Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars NIPS 2023
Masked Prediction: A Parameter Identifiability View NIPS 2022
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments NIPS 2022
Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions NIPS 2022
Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods COLT 2022
An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization AISTATS 2022
Contrasting the landscape of contrastive and non-contrastive learning AISTATS 2022
The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders ICLR 2022
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias ICLR 2022
Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation ICLR 2022
The Limitations of Limited Context for Constituency Parsing IJCNLP 2021
Universal Approximation Using Well-Conditioned Normalizing Flows NIPS 2021
Parametric Complexity Bounds for Approximating PDEs with Neural Networks NIPS 2021
The Limitations of Limited Context for Constituency Parsing ACL 2021
Contrastive learning of strong-mixing continuous-time stochastic processes AISTATS 2021
Efficient sampling from the Bingham distribution ALT 2021
The Risks of Invariant Risk Minimization ICLR 2021
Representational aspects of depth and conditioning in normalizing flows ICML 2021
On Learning Language-Invariant Representations for Universal Machine Translation ICML 2020
Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models ICML 2020
Approximability of Discriminators Implies Diversity in GANs ICLR 2019
Sum-of-squares meets square loss: Fast rates for agnostic tensor completion COLT 2019
The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent Structure ICLR 2019
Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo NIPS 2018
Do GANs learn the distribution? Some Theory and Empirics ICLR 2018
On the Ability of Neural Nets to Express Distributions COLT 2017
How to calculate partition functions using convex programming hierarchies: provable bounds for variational methods COLT 2016
Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods NIPS 2016
Recovery guarantee of weighted low-rank approximation via alternating minimization ICML 2016
Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates NIPS 2016
Algorithms and matching lower bounds for approximately-convex optimization NIPS 2016
Label optimal regret bounds for online local learning COLT 2015
On some provably correct cases of variational inference for topic models NIPS 2015