4 papers
Reshaping Global Loop Structure to Accelerate Local Optimization by Smoothing Rugged Landscapes
Timothee Leleu, Sam Reifenstein, Atsushi Yamamura +1
Probabilistic graphical models with frustration exhibit rugged energy landscapes that trap iterative optimization dynamics. These landscapes are shaped not only by local interactio…
The geometry and dynamics of annealed optimization in the coherent Ising machine with hidden and planted solutions
Federico Ghimenti, Adithya Sriram, Atsushi Yamamura +2
The coherent Ising machine (CIM) is a nonconventional hardware architecture for finding approximate solutions to large-scale combinatorial optimization problems. It operates by ann…
Fooling LLM graders into giving better grades through neural activity guided adversarial prompting
Atsushi Yamamura, Surya Ganguli
The deployment of artificial intelligence (AI) in critical decision-making and evaluation processes raises concerns about inherent biases that malicious actors could exploit to dis…
Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
Feng Chen, Daniel Kunin, Atsushi Yamamura +1
In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overly expressive networks to much simpler subnetworks, thereby dramatically reducin…