11 papers
Preference-Based Reward Learning under Partial Observability with Inexact Dynamics
Reza Zolnouri, Semih Cayci
In this paper, we study how partial observability and inexact latent-state inference affect reward learning from preferences. To that end, we study preference-based reward learning…
Finite-Time Analysis of Gradient Descent for Shallow Transformers
Enes Arda, Semih Cayci, Atilla Eryilmaz
Understanding why Transformers perform so well remains challenging due to their non-convex optimization landscape. In this work, we analyze a shallow Transformer with independe…
Convergence of Stochastic Gradient Langevin Dynamics in the Lazy Training Regime
Noah Oberweis, Semih Cayci
Continuous-time models provide important insights into the training dynamics of optimization algorithms in deep learning. In this work, we establish a non-asymptotic convergence an…
A Riemannian Optimization Perspective of the Gauss-Newton Method for Feedforward Neural Networks
Semih Cayci
In this work, we establish non-asymptotic convergence bounds for the Gauss-Newton method in training neural networks with smooth activations. In the underparameterized regime, the…
Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes
Johannes Müller, Semih Cayci
We study the error introduced by entropy regularization in infinite-horizon discrete discounted Markov decision processes. We show that this error decreases exponentially in the in…
Non-Asymptotic Optimization and Generalization Bounds for Stochastic Gauss-Newton in Overparameterized Models
Semih Cayci
An important question in deep learning is how higher-order optimization methods affect generalization. In this work, we analyze a stochastic Gauss-Newton (SGN) method with Levenber…