finding

active

finding:nis-outperforms-nis-variational-autoencoders-and-feed-forward-neural-networks-in-out-of-distribution-generalization-experiments

NIS+ outperforms NIS, variational autoencoders, and feed-forward neural networks in out-of-distribution generalization experiments.

Yang et al. (2023) result linking EI maximization to robust generalization.

Source paper

extracted_from

Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studies

(2023) · Bing Yuan · Jiang Zhang · Aobo Lyu · Jiayun Wu +5

Neighborhood — ranked by edge-count

Claims (1)

claim

EI and normalized EI could serve as a unified metric for out-of-distribution generalization.
supports
Conjecture that maximizing EI yields causal representations invariant to distribution shifts.

Communities (3)

community

Causal emergence in biological systems
members_of
Examines how macro-scale causal power exceeds micro-scale in living and learning systems.
Causal emergence in learning agents
members_of
Uses effective information (EI) and coarse-graining to link causal emergence with RL and biological learning.
Causal emergence via information-geometric coarse-graining
members_of
Framework using effective information (EI) and NIS+ to automatically discover macro-scale dynamics from micro-level data, validated on fMRI, Conway's Game of Life, and SIR models.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

NIS+ learns macro-dynamics matching ground-truth SIR dynamics from noisy micro-level data.finding0.781
Experimental result from Yang et al. (2023) reported in the survey.
Winner take-all architectures of decision-making are already commonplace in computational neuroscience, and the softmax function provides a smooth approximation.claim0.761
Neural plausibility argument for softmax policy selection.
The NIS and NIS+ frameworks provide effective solutions for causal emergence identification from data.claim0.759
Central claim of the machine-learning section, summarizing the contribution.
All neuronal processing and action selection minimize variational free energy, unifying perception, action, and learning.claim0.758
Fundamental assertion: single imperative (free energy minimization) explains diverse cognitive and neural phenomena.
NIS+ captures emergent static/dynamic patterns such as 'gliders' in Conway's Game of Life within the latent space.finding0.757
Yang et al. (2023) demonstration of emergent pattern recognition.
Physical systems are more constrained in learning abilities than in silico neural networks due to locality requirements, but this mirrors biological learning constraints and offers robustness benefitsclaim0.755
Core theoretical claim establishing that locality constraints in physical learning are not fatal—they reflect biological precedent and provide advantages like robustness and scalability
NIS+ automatically discovers two-group macro-states in Boid model simulations matching the two boid groups.finding0.755
Yang et al. (2023) experiment on emergent herding behavior.
DAS overcomes the localist limitation of prior causal abstraction by allowing individual neurons to play multiple roles via non-standard basesclaim0.747
Central claim motivating DAS over prior methods.