REVIEW 19 cited by
Importance Weighted Autoencoders
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Importance Weighted Autoencoders
read the original abstract
The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong assumptions about posterior inference, for instance that the posterior distribution is approximately factorial, and that its parameters can be approximated with nonlinear regression from the observations. As we show empirically, the VAE objective can lead to overly simplified representations which fail to use the network's entire modeling capacity. We present the importance weighted autoencoder (IWAE), a generative model with the same architecture as the VAE, but which uses a strictly tighter log-likelihood lower bound derived from importance weighting. In the IWAE, the recognition network uses multiple samples to approximate the posterior, giving it increased flexibility to model complex posteriors which do not fit the VAE modeling assumptions. We show empirically that IWAEs learn richer latent space representations than VAEs, leading to improved test log-likelihood on density estimation benchmarks.
Forward citations
Cited by 19 Pith papers
-
Density estimation using Real NVP
Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations.
-
When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?
Synthetic minority augmentation improves threshold-integrated and optimized classification metrics only under model misspecification by correcting ranking errors, while providing no fundamental benefit beyond possible...
-
Resampling in conditional SMC algorithms
A general framework for valid resampling in SMC and CSMC that handles most known schemes, including exotic ones, under only weak assumptions and without random permutation of ancestor indices.
-
A Hybrid Generative Reduced-Order Model for the Minimal Flow Unit
A β-VAE-GAN plus sensor-conditioned Transformer with Easy Attention forecasts near-wall turbulence in the Minimal Flow Unit, recovering 87% turbulent kinetic energy in 4D latent space and maintaining accuracy over 172...
-
End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems
Identifiability is proven for recurrent nonlinear switching dynamical systems under flexible assumptions, and ΩSDS is introduced as a flow-based estimator that improves disentanglement and forecasting over VAE-based methods.
-
Learning to Theorize the World from Observation
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven gener...
-
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.
-
Revisiting the Volume Hypothesis
The generalization advantage of SGD over random sampling diminishes with growing training set size in binary networks, as measured by joint density of states over train and test accuracy.
-
Grouped Reverse Importance Sampling for the Partition Function
Grouped reverse importance sampling reduces MSE in partition function estimation by 20-65% for k=2,3 using group-energy dependent weights that couple samples without product form.
-
H\"older++: Improving the Quality-Coherence Trade-off in Multimodal VAEs
Hölder++ improves the quality-coherence trade-off in multimodal VAEs via exact Hölder pooling, shared-private latent modeling, and hierarchical inference.
-
Efficient Learning of Deep State Space Models via Importance Smoothing
PVMC is a new parallel training algorithm for deep state space models that achieves 10x faster training than prior SMC methods while matching or exceeding benchmark performance for both generative and discriminative tasks.
-
Efficient Learning of Deep State Space Models via Importance Smoothing
Introduces PVMC, a parallelizable training method for deep state space models that claims state-of-the-art results and 10x faster training than prior SMC approaches.
-
Continuous Diffusion Scales Competitively with Discrete Diffusion for Language
RePlaid achieves a 20x compute gap to autoregressive models, new SOTA PPL of 22.1 among continuous DLMs on OpenWebText, and competitive scaling laws by aligning architecture with modern discrete DLMs.
-
A renormalization-group inspired lattice-based framework for piecewise generalized linear models
RG-inspired lattice models for piecewise GLMs provide explicit interpretable partitions and a replica-analysis-derived scaling law for regularization that allows increasing complexity without expected rise in generali...
-
Learning to Theorize the World from Observation
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markov...
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer achieves state-of-the-art results in offline goal-conditioned RL by replacing return-to-go with a state-conditioned Q-estimator and introducing a gated hybrid attention-mamba backbone for content-adaptive histor...
-
Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning
R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.
-
Mitigating Barren Plateaus in Quantum Denoising Diffusion Probabilistic Model
Quantum diffusion models develop a distinct barren plateau beyond small qubit counts; an architectural enhancement and conditional formulation restore trainability for Hamiltonian-parameterized ground-state generation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.