Self-referential meta learning avoids explicit optimization by modifying itself.
problem Dependency on human engineering in meta learning algorithms.
method Investigates self-referential meta learning systems that modify themselves without explicit optimization.
result Self-referential neural networks can improve their own modifications without explicit optimization.
Cycles in causal learning cause feedback loops under intervention.
problem Cyclic causal structures lead to feedback loops in causal inference.
method Theoretical observations about self-referential distributions and their factorizations.
result Cyclic causal dependence can exist even when observational data suggest independence.
New phenomena in 4-manifolds show discs with special properties.
problem Exploring special properties of discs in 4-manifolds.
method Construction of discs with geometrically dual spheres and analysis of isotopy.
result Discs with common geometrically dual spheres are not properly isotopic but are otherwise related.
We introduce a method to infer lead-lag networks of agents' actions in complex systems. These networks open the way to both microscopic and macroscopic states prediction in such systems. We apply this method to trader-resolved data in the foreign exchange market. We show that these networks are remarkably persistent, w…
FHRN uses continuous-time dynamics to stabilize reentrant neural computation.
problem Stabilizing reentrant neural computation.
method Formulated as a continuous-time neural-ODE system, revealing norm-regulated reentry.
result Achieves stable oscillatory trajectories through population-level gain modulation.
Sharp pseudospectral bounds prevent transient amplification in coupled gradient descent.
problem Transient amplification in coupled gradient descent systems.
method Developed a sharp pseudospectral theory for block-triangular Jacobians, proving Kreiss constant bounds and matching minimax lower bounds.
result Obtained a finite-horizon iteration-complexity bound of O ( K ( J ) 2 log ( 1 / δ ) ) O(K(J)^2 \log(1/δ)) O ( K ( J ) 2 log ( 1/ δ )) for stochastic coupled descent. Revisits elastic string model to explain interest rate correlations.
problem Describing the forward interest rate curve using an elastic string model.
method Reinterprets Baaquie and Bouchaud's (2004) model to highlight market forces.
result Model accurately reproduces FRC correlation structure with minimal parameters.
Financial and economic history is strewn with bubbles and crashes, booms and busts, crises and upheavals of all sorts. Understanding the origin of these events is arguably one of the most important problems in economic theory. In this paper, we review recent efforts to include heterogeneities and interactions in models…
Mathematical framework using Riemannian geometry for intelligence and consciousness.
problem Lack of a unified mathematical framework for intelligence and consciousness.
method Conceptualizes intelligence as tokens in a high-dimensional space, using Riemannian geometry to describe structure and dynamics.
result Integrates geometric concepts to offer a unified framework for intelligence and consciousness.
Study shows how to improve contextual bandits with loss predictors.
problem Improving minimax regret in contextual bandits with loss predictors.
method Developed novel algorithmic techniques for upper bounds and lower bounds in various settings.
result Optimal regret is O ( min { T , E T 1 4 } ) \mathcal{O}(\min\{\sqrt{T}, \sqrt{\mathcal{E}}T^\frac{1}{4}\}) O ( min { T , E T 4 1 }) when E \mathcal{E} E is known, and O ( E T 1 3 ) \mathcal{O}(\sqrt{\mathcal{E}}T^\frac{1}{3}) O ( E T 3 1 ) if E \mathcal{E} E is unknown.