4 papers
Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization
Sharan Sahu, Abir Sarkar, Cameron J. Hogan +1
We provide a theoretical analysis of Adam under non-stationary stochastic objectives, separating two regimes: Euclidean tracking under adaptive strong monotonicity of the Adam-prec…
On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
Sharan Sahu, Cameron J. Hogan, Martin T. Wells
In this paper, we provide a comprehensive theoretical analysis of Stochastic Gradient Descent (SGD) and its momentum variants (Polyak Heavy-Ball and Nesterov) for tracking time-var…
Quantum Geometry of Data
Alexander G. Abanov, Luca Candelori, Harold C. Steinacker +9
We demonstrate how Quantum Cognition Machine Learning (QCML) encodes data as quantum geometry. In QCML, features of the data are represented by learned Hermitian matrices, and data…
Robust estimation of the intrinsic dimension of data sets with quantum cognition machine learning
Luca Candelori, Alexander G. Abanov, Jeffrey Berger +8
We propose a new data representation method based on Quantum Cognition Machine Learning and apply it to manifold learning, specifically to the estimation of intrinsic dimension of…