Country
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers Lorenzo Tiberi 1,2 Francesca Mignacco
Second, generalization--what specific aspects of the transformer architecture are responsible for their effective learning?
Efficient Training of Energy-Based Models Using Jarzynski Equality
Their performance is well measured by the cross-entropy (CE) of the model distribution relative to the data distribution.
Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products
Some related lower bounds include the work of Backurs et al. [2017] that solving kernel Support V ector Machines (SVM), ridge regression, or Principal Component Analysis (PCA) problems to high accuracy or approximating kernel density estimates up to a constant factor for kernels with
Accelerating ERM for data-driven algorithm design using output-sensitive techniques
Data-driven algorithm design is a promising, learning-based approach for beyond worst-case analysis of algorithms with tunable parameters. An important open problem is the design of computationally efficient data-driven algorithms for combinatorial algorithm families with multiple parameters.
