A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Transformer models align words through attention weights, closely approximating Optimal Transport.
problem Understanding the internal mechanism of transformer models in language processing.
method Empirical evidence and theoretical analysis of attention weights and their relation to Optimal Transport.
result Transformer models can simulate gradient descent on the dual of entropy-regularized OT problem, providing a theoretical foundation for token alignment.
We address the problem of image translation between domains or modalities for which no direct paired data is available (i.e. zero-pair translation). We propose mix and match networks, based on multiple encoders and decoders aligned in such a way that other encoder-decoder pairs can be composed at test time to perform u…
Deep Gaussian Processes with polynomial kernels can collapse rapidly without proper hyperparameter tuning.
problem The collapse of Deep Gaussian Processes with polynomial kernels without careful hyperparameter tuning.
method Analysis using the Berry-Esseen Theorem and observation of prior behavior.
result The prior of a Deep Gaussian Process collapses rapidly towards zero or places negligible mass on low norm functions without proper hyperparameter tuning.
Maximal initial learning rate for deep ReLU networks identified.
problem Finding the optimal initial learning rate for deep neural networks.
method Simple approach to estimate maximal initial learning rate η∗, analyzing its behavior in constant-width fully-connected ReLU networks.
result Maximal initial learning rate η∗ is well predicted as a power of depth × width, with specific conditions for network width and input layer training.
The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the GPT-2 small pretrained model. We visualize attention for individual instances and…
Unified analysis of generalization and sample complexity for semi-supervised domain adaptation.
problem Theoretical foundations of domain adaptation remain underexplored, especially for modern approaches.
method Unified theoretical study of domain adaptation algorithms based on domain alignment, considering joint learning of feature transformations and shared classifiers in a semi-supervised setting.
result Unified theoretical analysis of domain adaptation algorithms, providing generalization bounds and sample complexity bounds for MMD and adversarial models.
Learning based methods have shown very promising results for the task of depth estimation in single images. However, most existing approaches treat depth prediction as a supervised regression problem and as a result, require vast quantities of corresponding ground truth depth data for training. Just recording quality d…
Following the seminal idea of Tukey, data depth is a function that measures how close an arbitrary point of the space is located to an implicitly defined center of a data cloud. Having undergone theoretical and computational developments, it is now employed in numerous applications with classification being the most po…
ResNets and their GP generalization align ideas via function space warping, revealing robust properties and connections to image registration.
problem Aligning abstract shapes (ideas) using neural networks.
method Introducing a generalization of ResNets as a GP, showing convergence to image registration variational algorithms, and revealing properties via a Hamiltonian interpretation.
result ResNets and their GP generalization align ideas via function space warping, revealing robust properties and connections to image registration.
Proposes a new method to estimate Bayesian neural network depth.
problem Estimating the depth of Bayesian neural networks.
method Uses a discrete truncated normal distribution to learn depth mean and variance, inferring posterior distributions by minimizing variational free energy.
result Improves test accuracy and reduces posterior depth variance on the spiral dataset.
Analysis of deep neural networks under various learning rules reveals dynamics of feature and prediction learning.
problem Understanding how different learning rules affect feature and prediction dynamics in deep neural networks.
method Analysis of infinite-width deep networks trained with gradient descent and various learning rules.
result The evolution of the output function is governed by an effective neural tangent kernel (eNTK), which varies depending on the learning rule and training regime.