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.
FEM improves attention mechanisms by applying value-driven log-linear tilts.
In this paper, we introduce Channel-wise recurrent convolutional neural networks (RecNets), a family of novel, compact neural network architectures for computer vision tasks inspired by recurrent neural networks (RNNs). RecNets build upon Channel-wise recurrent convolutional (CRC) layers, a novel type of convolutional …
The successive subspace learning (SSL) principle was developed and used to design an interpretable learning model, known as the PixelHop method,for image classification in our prior work. Here, we propose an improved PixelHop method and call it PixelHop++. First, to make the PixelHop model size smaller, we decouple a j…
We propose a dynamic neighborhood aggregation (DNA) procedure guided by (multi-head) attention for representation learning on graphs. In contrast to current graph neural networks which follow a simple neighborhood aggregation scheme, our DNA procedure allows for a selective and node-adaptive aggregation of neighboring …
A new method for early stopping in neural networks without validation sets.
As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this problem by branching networks, or by a channel-wise modulation of the network feature…
We propose doubly nested network(DNNet) where all neurons represent their own sub-models that solve the same task. Every sub-model is nested both layer-wise and channel-wise. While nesting sub-models layer-wise is straight-forward with deep-supervision as proposed in \cite{xie2015holistically}, channel-wise nesting has…
A new distillation method transfers channel information from teacher to student.
Deep convolutional neural networks are known to be unstable during training at high learning rate unless normalization techniques are employed. Normalizing weights or activations allows the use of higher learning rates, resulting in faster convergence and higher test accuracy. Batch normalization requires minibatch sta…
SAMformer improves transformer performance in time series forecasting.
Attention operators have been widely applied in various fields, including computer vision, natural language processing, and network embedding learning. Attention operators on graph data enables learnable weights when aggregating information from neighboring nodes. However, graph attention operators (GAOs) consume exces…
Neural network pruning is an important step in design process of efficient neural networks for edge devices with limited computational power. Pruning is a form of knowledge transfer from the weights of the original network to a smaller target subnetwork. We propose a new method for compute-constrained structured channe…
DecompKAN improves time series forecasting accuracy and transparency.
ESE-FN improves elderly activity recognition accuracy.
A new data-level recombination strategy improves RGB-D salient object detection.
A new model classifies multi-lead ECGs better than single-channel models.
Mind wandering (MW) is a ubiquitous phenomenon which reflects a shift in attention from task-related to task-unrelated thoughts. There is a need for intelligent interfaces that can reorient attention when MW is detected due to its detrimental effects on performance and productivity. In this paper, we propose a deep lea…
Random layer-wise pruning profiles are as effective as metric-based ones for various datasets.
A new method normalizes activations to match batch normalization without batch dependence.
Multi-step passenger demand forecasting is a crucial task in on-demand vehicle sharing services. However, predicting passenger demand over multiple time horizons is generally challenging due to the nonlinear and dynamic spatial-temporal dependencies. In this work, we propose to model multi-step citywide passenger deman…
A fall is an abnormal activity that occurs rarely, so it is hard to collect real data for falls. It is, therefore, difficult to use supervised learning methods to automatically detect falls. Another challenge in using machine learning methods to automatically detect falls is the choice of engineered features. In this p…
We propose to impose symmetry in neural network parameters to improve parameter usage and make use of dedicated convolution and matrix multiplication routines. Due to significant reduction in the number of parameters as a result of the symmetry constraints, one would expect a dramatic drop in accuracy. Surprisingly, we…
Wind power, as an alternative to burning fossil fuels, is abundant and inexhaustible. To fully utilize wind power, wind farms are usually located in areas of high altitude and facing serious ice conditions, which can lead to serious consequences. Quick detection of blade ice accretion is crucial for the maintenance of …
Tent adapts models during testing by minimizing entropy of predictions.
Improved flow-based models capture dependencies better with multi-scale autoregressive priors.
ShuffleNet is a state-of-the-art light weight convolutional neural network architecture. Its basic operations include group, channel-wise convolution and channel shuffling. However, channel shuffling is manually designed empirically. Mathematically, shuffling is a multiplication by a permutation matrix. In this paper, …
Within the context of multivariate time series segmentation this paper proposes a method inspired by a posteriori optimal trading. After a normalization step time series are treated channel-wise as surrogate stock prices that can be traded optimally a posteriori in a virtual portfolio holding either stock or cash. Line…
Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels are in effect re-learning redundant data. In this work, we show that this redund…
Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular network connections that not only demand extra representation efforts but also …
New method improves accuracy of quantized neural networks.
Majority of semantic segmentation algorithms operate on a single frame even in the case of videos. In this work, the goal is to exploit temporal information within the algorithm model for leveraging motion cues and temporal consistency. We propose two simple high-level architectures based on Recurrent FCN (RFCN) and Mu…
Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable. Spiking neural networks (SNNs) have attracted widespread interest as the third-g…
AverageTime uses simple averaging to enhance long-term time series forecasting.
This paper evaluates anomaly detection methods for multivariate time series data.
Model classifies hand gestures with low EMG samples augmented with noise.
New method estimates selection event for black-box models.
Cluster stability selection improves feature selection in correlated data.
New method corrects selection bias in post-selective inference for Group LASSO.
Proposes PEMI for online selective conformal prediction with asymmetric rules.
The paper addresses errors in online selective conformal prediction and proposes new strategies to ensure valid inference.
This work develops scalable model selection methods with fast update and selection.
Online method selects candidates from data streams, ensuring irreversible decisions.
Paper improves -NN predictive performance with efficient variable selection.
Value selection reduces model size while maintaining accuracy.
Proposes HSIC-Lasso for selective inference in non-linear data.
Paper proposes a statistical test for feature selection pipelines using selective inference.
New method improves feature selection by integrating stability paths.
UniFeat is an open-source Java tool for feature selection.