Cover Image

Double Descent as a Lens for Sample Efficiency in Autoregressive vs. Discrete Diffusion Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fraij, Ahmad, Dauncey, Sam
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EBGAN-MDN: An Energy-Based Adversarial Framework for Multi-Modal Behavior Cloning
by: Li, Yixiao, et al.
Published: (2025)

Subliminal Signals in Preference Labels
by: Magistrali, Isotta, et al.
Published: (2026)

Approximations to the Fisher Information Metric of Deep Generative Models for Out-Of-Distribution Detection
by: Dauncey, Sam, et al.
Published: (2024)

Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
by: Gu, Yufei, et al.
Published: (2023)

Multi-scale Autoregressive Models are Laplacian, Discrete, and Latent Diffusion Models in Disguise
by: Hong, Steve, et al.
Published: (2025)

Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning
by: Berrayana, Lina, et al.
Published: (2026)

Improved Sampling Schedules for Discrete Diffusion Models
by: Foresti, Alberto, et al.
Published: (2026)

Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End
by: Hanneke, Steve, et al.
Published: (2026)

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning
by: Ye, Jiacheng, et al.
Published: (2024)

Bayesian Double Descent
by: Polson, Nick, et al.
Published: (2025)

Manipulating Sparse Double Descent
by: Zhang, Ya Shi
Published: (2024)

Planner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning
by: Berrayana, Lina, et al.
Published: (2025)

Analog Physical Systems Can Exhibit Double Descent
by: Dillavou, Sam, et al.
Published: (2025)

Discrete Diffusion with Sample-Efficient Estimators for Conditionals
by: Elamvazhuthi, Karthik, et al.
Published: (2026)

Simple Guidance Mechanisms for Discrete Diffusion Models
by: Schiff, Yair, et al.
Published: (2024)

Dropout Drops Double Descent
by: Yang, Tian-Le, et al.
Published: (2023)

NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
by: Liu, Enshu, et al.
Published: (2026)

Double Descent and Other Interpolation Phenomena in GANs
by: Luzi, Lorenzo, et al.
Published: (2021)

On the Lipschitz Constant of Deep Networks and Double Descent
by: Gamba, Matteo, et al.
Published: (2023)

Discrete State Diffusion Models: A Sample Complexity Perspective
by: Srikanth, Aadithya, et al.
Published: (2025)

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall
by: Jo, Mingyu, et al.
Published: (2025)

Learning Generation Orders for Masked Discrete Diffusion Models via Variational Inference
by: Fox, David, et al.
Published: (2026)

DDPS: Discrete Diffusion Posterior Sampling for Paths in Layered Graphs
by: Luan, Hao, et al.
Published: (2025)

Double Descent: Understanding Linear Model Estimation of Nonidentifiable Parameters and a Model for Overfitting
by: Christensen, Ronald
Published: (2024)

Discriminator Guidance for Autoregressive Diffusion Models
by: Kelvinius, Filip Ekström, et al.
Published: (2023)

MBDP: A Model-based Approach to Achieve both Robustness and Sample Efficiency via Double Dropout Planning
by: Zhang, Wanpeng, et al.
Published: (2021)

Masked Diffusion Models are Secretly Learned-Order Autoregressive Models
by: Garg, Prateek, et al.
Published: (2025)

Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
by: Dmitriev, Daniil, et al.
Published: (2026)

Teaching Metric Distance to Discrete Autoregressive Language Models
by: Chung, Jiwan, et al.
Published: (2025)

On The Presence of Double-Descent in Deep Reinforcement Learning
by: Veselý, Viktor, et al.
Published: (2025)

Class-wise Activation Unravelling the Engima of Deep Double Descent
by: Gu, Yufei
Published: (2024)

Arch-VQ: Discrete Architecture Representation Learning with Autoregressive Priors
by: Poddenige, Deshani Geethika, et al.
Published: (2025)

Correlations Are Ruining Your Gradient Descent
by: Ahmad, Nasir
Published: (2024)

Gradient Descent Efficiency Index
by: Dhingra, Aviral
Published: (2024)

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
by: Arriola, Marianne, et al.
Published: (2025)

AUTODIFF: Autoregressive Diffusion Modeling for Structure-based Drug Design
by: Li, Xinze, et al.
Published: (2024)

Split Gibbs Discrete Diffusion Posterior Sampling
by: Chu, Wenda, et al.
Published: (2025)

DEER: Draft with Diffusion, Verify with Autoregressive Models
by: Cheng, Zicong, et al.
Published: (2025)

Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource Hardware
by: Gupta, Srishti, et al.
Published: (2025)

The Double Descent Behavior in Two Layer Neural Network for Binary Classification
by: Abeykoon, Chathurika S, et al.
Published: (2025)