technique
Jerrum-Sinclair backtracking Markov chain
techniqueactiveprovisional
jerrum-sinclair-backtracking-markov-chain-5b04d97c·1 events·first seen 17h agoAliases: Jerrum-Sinclair backtracking Markov chain
Co-occurring entities
More like this (12)
Behavioral Trajectory Tracking FrameworkKnowledge Graph Random WalkHamiltonian leapfrog mapEntropy-Cut Metropolis-HastingsAIR: Adaptive Interleaved Reasoning with Code in MLLMsFollow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor TokensExpRL: Exploratory RL for LLM Mid-TrainingForward-Forward AlgorithmMinimum Bayes Risk DecodingReroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language ModelsGumbel noise steeringLangevin Dynamics
Recent events (1)
MDM-VGB: Theoretically grounded test-time scaling for masked diffusion models via reward-guided remasking
Researchers introduce MDM-VGB, a discrete diffusion sampler for Masked Diffusion Models that augments token unmasking with reward-guided remasking inspired by the Jerrum-Sinclair backtracking Markov chain. The method extends backtracking from a fixed prefix tree to a masked-state graph, enabling tokens to be unmasked and remasked at arbitrary positions to favor higher-reward partial configurations. The authors prove quadratic complexity and robustness to process-verifier noise, contrasting with exponential complexity of best-of-N heuristics, and validate on constraint-satisfaction benchmarks including Sudoku and QM9.