arXiv research

Improved U-Nets with various intermediate blocks enhance singing voice separation.

Knowledge distillation (KD) is a popular method for reducing the computational overhead of deep network inference, in which the output of a teacher model is used to train a smaller, faster student model. Hint training (i.e., FitNets) extends KD by regressing a student model's intermediate representation to a teacher mo…

Improved EXACT strategy reduces GNN memory consumption and runtime.

We study the problem of computing the matrix exponential of a block triangular matrix in a peculiar way: Block column by block column, from left to right. The need for such an evaluation scheme arises naturally in the context of option pricing in polynomial diffusion models. In this setting a discretization process pro…

Bottom-up algorithms outperform top-down in hierarchical community detection at intermediate levels.

The paper explores IL and LVR in AMMs, identifying three regimes and the effect of fees.

UniPhyNet improves cognitive load classification accuracy using EEG, ECG, and EDA signals.

BlockEcho method improves imputation of block-wise missing data.

Paper analyzes why deeper layers of ViTs perform worse on out-of-distribution tasks.

In high dimensions, find paths connecting points with intermediate steps in a dense set.

The central discovery of $2d$ conformal theory was holomorphic factorization, which expressed correlation functions through bilinear combinations of conformal blocks, which are easily cut and joined without a need to sum over the entire huge Hilbert space of states. Somewhat similar, when a link diagram is glued from t…

We consider the problem of estimating the location of a single change point in a dynamic stochastic block model. We propose two methods of estimating the change point, together with the model parameters. The first employs a least squares criterion function and takes into consideration the full structure of the stochast…

In this paper, we propose a new method called ProfWeight for transferring information from a pre-trained deep neural network that has a high test accuracy to a simpler interpretable model or a very shallow network of low complexity and a priori low test accuracy. We are motivated by applications in interpretability and…

A new probabilistic BTD method for tensor data.

A new KD layer lets student models learn and apply teacher knowledge explicitly.

Innovative neural networks reduce memory usage for efficient, accurate segmentation.

This paper generalizes the envelope of mid-lines to intermediate lines for a plane curve.

Study on rigidity with non-negative intermediate curvature on low-dimensional manifolds.

Preserves positive intermediate curvature on manifolds.

The study connects manifold topology to metrics with positive intermediate curvature.

New rigidity results for manifolds with maximal symmetry rank and positive intermediate Ricci curvature.

Study on spaces of metrics with intermediate curvature bounds.

Proves metrics with positive intermediate Ricci curvature on complex manifolds.

Extends Perelman's theorem to positive intermediate curvature conditions.

The study proves that certain manifolds with boundary cannot have metrics with positive intermediate curvatures.

Study finds metrics with positive intermediate Ricci curvature on specific low-dimensional manifolds.

Sharp dimension constraints for positive intermediate curvature metrics are established.

This paper introduces a novel approach to measuring privacy risks in deep computer vision models based on intermediate outputs.

This paper presents a method for solving the supervised learning problem in which the output is highly nonlinear and discontinuous. It is proposed to solve this problem in three stages: (i) cluster the pairs of input-output data points, resulting in a label for each point; (ii) classify the data, where the correspondin…

The paper proves manifold splitting theorems with nonnegative intermediate curvature.

In this work, we introduce the Global Planar Convolution module as a building-block for fully-convolutional networks that aggregates global information and, therefore, enhances the context perception capabilities of segmentation networks in the context of brain tumor segmentation. We implement two baseline architecture…

A framework to explain decoder-only sequence classification models using intermediate predictions.

Polyhedral semantics for intermediate logics; Nerve Criterion ensures completeness.

We use a local argument to prove if an $r$-dimensional torus acts isometrically and effectively on a connected $n$-dimensional manifold which has positive $k^\mathrm{th}$-intermediate Ricci curvature at some point, then $r \leq \lfloor \frac{n+k}{2} \rfloor$. This symmetry rank bound generalizes those established by Gr…

Spectral gradient methods outperform Euclidean in certain deep learning scenarios.

We give a homological construction of aperiodic tiles for certain open Riemannian surfaces admitting actions of Grigorchuk groups of intermediate growth.

Post-hoc explanations improve CNNs by replacing final linear layer with k-means classifier.

A cost-effective framework for gradual domain adaptation using multifidelity.

This work tackles representation learning by introducing stochastic competition-based activations.

Gradual domain adaptation improves model transfer between domains with intermediate training.

Study shows Gromov's Betti number bound fails for certain intermediate Ricci curvatures.

This paper proposed a new regression model called $l_1$-regularized outlier isolation and regression (LOIRE) and a fast algorithm based on block coordinate descent to solve this model. Besides, assuming outliers are gross errors following a Bernoulli process, this paper also presented a Bernoulli estimate model which, …

Study analyzes financial intermediation costs in decentralized lending protocols.

Intermediate logic of all convex polyhedra is axiomatized.

Study estimates heterogeneous principal causal effects with binary treatments and intermediate variables.

Log-Sobolev inequality proven for submanifolds in specific types of manifolds.

Optimizes transport on submanifolds for curvature inequalities.

We study an optimal execution problem in the presence of market impact where the security price follows a geometric Ornstein-Uhlenbeck process, which implies the mean-reverting property, and show that the optimal strategy is a mixture of initial/terminal block liquidation and gradual intermediate liquidation. The mean-…