Copertina

Steering diffusion models with quadratic rewards: a fine-grained analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Moitra, Ankur, Risteski, Andrej, Rohatgi, Dhruv
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Data Structures and Algorithms
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives
di: Moitra, Ankur, et al.
Pubblicazione: (2026)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Constant matters: Fine-grained Complexity of Differentially Private Continual Observation
di: Fichtenberger, Hendrik, et al.
Pubblicazione: (2022)

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

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

Fitting an ellipsoid to a quadratic number of random points
di: Bandeira, Afonso S., et al.
Pubblicazione: (2023)

Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
di: Gu, Yuzhou, et al.
Pubblicazione: (2024)

Simple, unified analysis of Johnson-Lindenstrauss with applications
di: Li, Yingru
Pubblicazione: (2024)

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

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

Tight Bounds for Learning Polyhedra with a Margin
di: Patel, Shyamal, et al.
Pubblicazione: (2026)

MNL-Bandit with Knapsacks: a near-optimal algorithm
di: Aznag, Abdellah, et al.
Pubblicazione: (2021)

Provably learning a multi-head attention layer
di: Chen, Sitan, et al.
Pubblicazione: (2024)

How fast can you find a good hypothesis?
di: Aamand, Anders, et al.
Pubblicazione: (2025)

Top-k on a Budget: Adaptive Ranking with Weak and Strong Oracles
di: Oettershagen, Lutz
Pubblicazione: (2026)

Fast White-Box Adversarial Streaming Without a Random Oracle
di: Feng, Ying, et al.
Pubblicazione: (2024)

Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
di: Chandrasekaran, Gautam, et al.
Pubblicazione: (2025)

Fast Adaptive Non-Monotone Submodular Maximization Subject to a Knapsack Constraint
di: Amanatidis, Georgios, et al.
Pubblicazione: (2020)

Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity
di: Amanatidis, Georgios, et al.
Pubblicazione: (2021)

The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
di: Abbe, Emmanuel, et al.
Pubblicazione: (2022)

On approximating the $f$-divergence between two Ising models
di: Feng, Weiming, et al.
Pubblicazione: (2025)

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

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

Efficient Adaptive Data Analysis over Dense Distributions
di: Huh, Joon Suk
Pubblicazione: (2026)

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

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