conftrace_

inductive biases

9 papers

Explore in graph

Co-occurring keywords · papers mentioning both

future values (1) historical data candidates (1) encoder (1) convergence properties (1) singular identifiability theory (1) low-complexity data (1) low-compute (1) low-memory (1) procedurally generated (1) deep linear recurrent unit (lru) (1)

Papers

Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry ICML 2025 From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph Transformers ICML 2025 Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research ICML 2025 Retrieval Augmented Time Series Forecasting ICML 2025 Position: The Causal Revolution Needs Scientific Pragmatism ICML 2024 Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning ICML 2024 Rethinking Transformers in Solving POMDPs ICML 2024 Scaling Down Deep Learning with MNIST-1D ICML 2024 Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning ICML 2024