5 papers
Well-Posed KL-Regularized Control via Wasserstein and Kalman-Wasserstein KL Divergences
Viktor Stein, Adwait Datar, Nihat Ay
Kullback-Leibler (KL) divergence regularization is widely used in reinforcement learning, but it becomes infinite under support mismatch and can degenerate in low-noise regimes. Us…
Beyond Silicon: Materials, Mechanisms, and Methods for Physical Neural Computing
Stefan Fischer, Nihat Ay, Olaf Landsiedel +4
Physical implementations of neural computation now extend far beyond silicon hardware, encompassing substrates such as memristive devices, photonic circuits, mechanical metamateria…
Wasserstein KL-divergence for Gaussian distributions
Adwait Datar, Nihat Ay
We introduce a new version of the KL-divergence for Gaussian distributions which is based on Wasserstein geometry and referred to as WKL-divergence. We show that this version is co…
Algorithmic bottlenecks in evolution: Genetic code, symbolic language, and the Great Filter hypothesis
Mikhail Prokopenko, Nihat Ay, Angelica Breviario +12
The Great Filter hypothesis proposes that the emergence of technological societies capable of interstellar travel depends on a small number of exceptionally hard and highly improba…
Convergence Properties of Natural Gradient Descent for Minimizing KL Divergence
Adwait Datar, Nihat Ay
The Kullback-Leibler (KL) divergence plays a central role in probabilistic machine learning, where it commonly serves as the canonical loss function. Optimization in such settings…