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.
A new framework for robot block-stacking tasks using causal probabilistic models.
Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot arm in simulation. Curiosity-driven exploration using the predict…
Generates biomedical abstracts from titles, years, and keywords.
Aims to create a world model without baggage, achieving good performance.
The deep network model, with the majority built on neural networks, has been proved to be a powerful framework to represent complex data for high performance machine learning. In recent years, more and more studies turn to nonneural network approaches to build diverse deep structures, and the Deep Stacking Network (DSN…
Algorithm solves robust linear regression with block Lewis weights.
OP3 models entities for better task generalization in reinforcement learning.
This paper introduces Non-Autonomous Input-Output Stable Network(NAIS-Net), a very deep architecture where each stacked processing block is derived from a time-invariant non-autonomous dynamical system. Non-autonomy is implemented by skip connections from the block input to each of the unrolled processing stages and al…
JKO-iFlow uses neural ODEs to improve generative models with reduced memory and training complexity.
HaKAN uses Hahn-KAN blocks to forecast multivariate time series.
Extended LSTM improves language modeling performance.
Deep learning has shown its great promise in various biomedical image segmentation tasks. Existing models are typically based on U-Net and rely on an encoder-decoder architecture with stacked local operators to aggregate long-range information gradually. However, only using the local operators limits the efficiency and…
Training-free looped transformers improve model performance without additional training.
Finding the best neural network architecture requires significant time, resources, and human expertise. These challenges are partially addressed by neural architecture search (NAS) which is able to find the best convolutional layer or cell that is then used as a building block for the network. However, once a good buil…
We introduce a new deep convolutional neural network, CrescendoNet, by stacking simple building blocks without residual connections. Each Crescendo block contains independent convolution paths with increased depths. The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks. In exp…
NoProp learns neural networks without full back-propagation or forward-propagation.
LoCo learns local representations without end-to-end synchronization, improving performance on complex tasks.
Optimal ensemble construction improves prediction accuracy for multi-study tasks, especially in pandemic scenarios.
N-BEATS-MOE improves time series forecasting by adapting to series characteristics.
In this paper, we propose two new algorithms for transduction with Matrix Completion (MC) problem. The joint MC and prediction tasks are addressed simultaneously to enhance the accuracy, i.e., the label matrix is concatenated to the data matrix forming a stacked matrix. Assuming the data matrix is of low rank, we propo…
This paper evaluates various representations for robotics tasks, improving performance in lifting, stacking, and pushing.
MSB framework improves survival prediction in immunotherapy patients with missing data.
In this study, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based design of Capsule Network architecture with two different feature extraction methods. In our design, Stacked-convolutional (SC) and Residual-connecte…
Stacking is a general approach for combining multiple models toward greater predictive accuracy. It has found various application across different domains, ensuing from its meta-learning nature. Our understanding, nevertheless, on how and why stacking works remains intuitive and lacking in theoretical insight. In this …
We review the basic definition of a stack and apply it to the topological and smooth settings. We then address two subtleties of the theory: the correct definition of a ``stack over a stack'' and the distinction between small stacks (which are algebraic objects) and large stacks (which are generalized spaces).
In this article, we derive many properties of étale stacks in various contexts, and prove that étale stacks may be characterized categorically as those stacks that arise as prolongations of stacks on a site of spaces and local homeomorphisms. Moreover, we show that the bicategory of étale differentiable stacks and loca…
Constructs cohomology decompositions for symmetric stacks.
Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the accumulation, deformation or dissipation of radar echoes in precipitation forecasting. Fr…
New neural stack and Turing Machine architectures prove stability and computational power.
Bayesian stacking improves model performance with varying model weights.
Currently there are two predominant ways to train deep neural networks. The first one uses restricted Boltzmann machine (RBM) and the second one autoencoders. RBMs are stacked in layers to form deep belief network (DBN); the final representation layer is attached to the target to complete the deep neural network. Autoe…
Paper combines machine learning and model averaging for robust parameter estimation.
We generalize the notion of a small sheaf of sets over a topological space or manifold to define the notion of a small stack of groupoids over an étale topological or differentiable stack. We then provide a construction analogous to the étalé space construction in this context, establishing an equivalence of 2-categori…
Multi-layered representation is believed to be the key ingredient of deep neural networks especially in cognitive tasks like computer vision. While non-differentiable models such as gradient boosting decision trees (GBDTs) are the dominant methods for modeling discrete or tabular data, they are hard to incorporate with…
This work characterizes global quotient stacks---smooth stacks associated to a finite group acting a manifold---among smooth quotient stacks , where is a smooth manifold equipped with a smooth proper action by a Lie group . The characterization is described in terms of the action of the connected componen…
The BPS decomposition theorem splits cohomology of symmetric stacks into invariant parts.
Stacked conformal prediction simplifies model validation.
Constructs moduli stacks for quiver connections and extends non-Abelian Hodge theory.
Constructs equivariant cohomology models for differentiable stacks.
In this paper, we consider diffeological spaces as stacks over the site of smooth manifolds, as well as the "underlying" diffeological space of any stack. More precisely, we consider diffeological spaces as so-called concrete sheaves and show that the Grothendieck construction sending these sheaves to stacks has a left…
Study connections on Lie groupoids and stacks using Atiyah sequences.
Constructs moduli stacks of quiver bundles and applies to Higgs bundles.
We present a probabilistic forecasting framework based on convolutional neural network for multiple related time series forecasting. The framework can be applied to estimate probability density under both parametric and non-parametric settings. More specifically, stacked residual blocks based on dilated causal convolut…
Tree-SMU enables strong compositional generalization in neural networks.
New potentials found for sheaves on Calabi-Yau 4-folds.
STanHop predicts multivariate time series with memory-enhanced capabilities.
This thesis is divided into four chapters. The first chapter discusses the relationship between stacks on a site and groupoids internal to the site. It includes a rigorous proof of the folklore result that there is an equivalence between the bicategory of internal groupoids and the bicategory of geometric stacks. The s…
Stacked LSTM networks improve traffic volume forecasting.