Cover Image

The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Moitra, Ankur, Risteski, Andrej, Rohatgi, Dhruv
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Data Structures and Algorithms
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Steering diffusion models with quadratic rewards: a fine-grained analysis
by: Moitra, Ankur, et al.
Published: (2026)

Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
by: Rohatgi, Dhruv, et al.
Published: (2025)

Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning
by: Golowich, Noah, et al.
Published: (2024)

On Learning Parities with Dependent Noise
by: Golowich, Noah, et al.
Published: (2024)

Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Diffusions
by: Qin, Yilong, et al.
Published: (2023)

A computational phase transition for learning-to-sample from Ising models
by: Risteski, Andrej, et al.
Published: (2026)

Better Models and Algorithms for Learning Ising Models from Dynamics
by: Gaitonde, Jason, et al.
Published: (2025)

Bypassing the Noisy Parity Barrier: Learning Higher-Order Markov Random Fields from Dynamics
by: Gaitonde, Jason, et al.
Published: (2024)

Overcomplete Tensor Decomposition via Koszul-Young Flattenings
by: Kothari, Pravesh K., et al.
Published: (2024)

Model Stealing for Any Low-Rank Language Model
by: Liu, Allen, et al.
Published: (2024)

Learning $\mathsf{AC}^0$ Under Graphical Models
by: Chandrasekaran, Gautam, et al.
Published: (2026)

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification
by: Rohatgi, Dhruv, et al.
Published: (2025)

Structure learning of Hamiltonians from real-time evolution
by: Bakshi, Ainesh, et al.
Published: (2024)

Learning quantum Hamiltonians at any temperature in polynomial time
by: Bakshi, Ainesh, et al.
Published: (2023)

Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps
by: Kelner, Jonathan, et al.
Published: (2024)

Theoretically Grounded Pruning of Large Ground Sets for Constrained, Discrete Optimization
by: Nath, Ankur, et al.
Published: (2024)

The graph alignment problem: fundamental limits and efficient algorithms
by: Ganassali, Luca
Published: (2024)

Connectivity augmentation is fixed-parameter tractable
by: Korhonen, Tuukka, et al.
Published: (2026)

Computing diverse pair of solutions for tractable SAT
by: Gima, Tatsuya, et al.
Published: (2024)

A Dobrushin condition for quantum Markov chains: Rapid mixing and conditional mutual information at high temperature
by: Bakshi, Ainesh, et al.
Published: (2025)

Discretely Beyond $1/e$: Guided Combinatorial Algorithms for Submodular Maximization
by: Chen, Yixin, et al.
Published: (2024)

Correlation detection in trees for planted graph alignment
by: Ganassali, Luca, et al.
Published: (2021)

High-dimensional estimation with missing data: Statistical and computational limits
by: Verchand, Kabir Aladin, et al.
Published: (2026)

Strong spatial mixing for colorings on trees and its algorithmic applications
by: Chen, Zongchen, et al.
Published: (2023)

High-Temperature Gibbs States are Unentangled and Efficiently Preparable
by: Bakshi, Ainesh, et al.
Published: (2024)

Towards characterizing the value of edge embeddings in Graph Neural Networks
by: Rohatgi, Dhruv, et al.
Published: (2024)

Optimal Prediction-Augmented Algorithms for Testing Independence of Distributions
by: Aliakbarpour, Maryam, et al.
Published: (2026)

Efficient Adaptive Data Analysis over Dense Distributions
by: Huh, Joon Suk
Published: (2026)

Near-optimal Swap Regret Minimization for Convex Losses
by: Hu, Lunjia, et al.
Published: (2026)

Approximating splits for decision trees quickly in sparse data streams
by: Tatti, Nikolaj
Published: (2026)

The Art of Being Difficult: Combining Human and AI Strengths to Find Adversarial Instances for Heuristics
by: Nikoleit, Henri, et al.
Published: (2026)

Online Learning with Limited Information in the Sliding Window Model
by: Braverman, Vladimir, et al.
Published: (2026)

Asymptotically Robust Learning-Augmented Algorithms for Preemptive FIFO Buffer Management
by: Hsieh, Wen-Han, et al.
Published: (2026)

New Bounds for Kernel Sums via Fast Spherical Embeddings
by: Wagner, Tal
Published: (2026)

Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift
by: Klivans, Adam R., et al.
Published: (2026)

Adaptive Power Iteration Method for Differentially Private PCA
by: Nguyen, Ta Duy, et al.
Published: (2026)

Incremental Strongly Connected Components with Predictions
by: Deng, Ronald, et al.
Published: (2026)

Finite Sample Bounds for Learning with Score Matching
by: Smedira, Devin, et al.
Published: (2026)

Deterministic Coreset for Lp Subspace
by: Chhaya, Rachit, et al.
Published: (2026)

Compact Conformal Subgraphs
by: Gollapudi, Sreenivas, et al.
Published: (2026)