4 papers
ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads
Şuayp Talha Kocabay, Talha Rüzgar Akkuş, Kamer Ali Yuksel
Weight-only quantization substantially reduces the storage of large language model (LLM) transformer blocks, but practical backends often retain the final language-modeling head (L…
Optimism as a Vulnerability: Deceptive Stackelberg Control of UCB Bandit Followers
Şuayp Talha Kocabay, Kerem Yalçın, Talha Rüzgar Akkuş
Upper Confidence Bound (UCB) algorithms guarantee sublinear regret for agents learning unknown stochastic environments, yet the same principle that makes them statistically efficie…
Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees
Şuayp Talha Kocabay, Talha Rüzgar Akkuş, Kerem Yalçın
Scientific discovery via symbolic regression is often viewed as statistically and computationally intractable because the hypothesis space of expressions grows combinatorially with…
Superpositional Gradient Descent: Harnessing Quantum Principles for Model Training
Ahmet Erdem Pamuk, Emir Kaan Özdemir, Şuayp Talha Kocabay
Large language models (LLMs) are increasingly trained with classical optimization techniques like AdamW to improve convergence and generalization. However, the mechanisms by which…