#amortized-inference News & Analysis

3 articles tagged with #amortized-inference. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AINeutralarXiv – CS AI · Jun 236/10

🧠

ACTIVA: Amortized Causal Effect Estimation via Transformer-based Variational Autoencoder

Researchers introduce ACTIVA, a transformer-based variational autoencoder designed to estimate causal interventional distributions from observational data without requiring intervention datasets. The model amortizes causal knowledge across tasks, enabling zero-shot inference and outperforming existing baselines on synthetic and biological datasets while reducing spurious correlations.

AIBullisharXiv – CS AI · Jun 16/10

🧠

Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression

Researchers introduce SimpliPy, a rule-based simplification engine that accelerates symbolic regression by 100x compared to SymPy, enabling the amortized neural symbolic regression method Flash-ANSR to match state-of-the-art genetic programming approaches while producing more concise expressions.

AIBullisharXiv – CS AI · Apr 106/10

🧠

Instance-Adaptive Parametrization for Amortized Variational Inference

Researchers introduce Instance-Adaptive VAE (IA-VAE), a new framework that uses hypernetworks to generate input-specific parameter modulations for variational autoencoders, reducing the amortization gap while maintaining computational efficiency. The approach demonstrates improved posterior approximation accuracy on synthetic data and consistently better ELBO performance on image benchmarks compared to standard VAEs.