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.
ETC improves Transformer models for long and structured inputs.
New framework interprets deep neural networks through input structure.
Model predicts composite structures assembly quality with input uncertainty.
SpinSVAR estimates SVAR models with sparse input, improving accuracy and scalability.
We find a normal form for two-input flat discrete-time systems.
Graph-to-Tree Neural Networks improve structured input-output translation in tasks like semantic parsing and math word problems.
Study of deep neural networks using finite-time Lyapunov exponents.
We consider the problem of learning a high-dimensional multi-task regression model, under sparsity constraints induced by presence of grouping structures on the input covariates and on the output predictors. This problem is primarily motivated by expression quantitative trait locus (eQTL) mapping, of which the goal is …
Paper presents a new triangular form for flat systems.
Deep learning models converge to Gaussian dynamics with mixed structured inputs.
A neural network finds causal relationships among latent variables.
Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these constraints and using them for supervision, bypassing the difficulty of using d…
MIMONets speed up neural network inference by processing multiple inputs in parallel.
LOL-BO improves latent space Bayesian optimization over structured inputs.
Sketching accelerates structured prediction methods for large datasets.
Extremely accurate prediction of dynamical system bifurcations using control inputs.
JacNet learns Jacobians to enforce structure on derivatives for invertibility and Lipschitz functions.
The problem of combined state and input estimation of linear structural systems based on measured responses and a priori knowledge of structural model is considered. A novel methodology using Gaussian process latent force models is proposed to tackle the problem in a stochastic setting. Gaussian process latent force mo…
Recurrent neural networks (RNNs) can model natural language by sequentially 'reading' input tokens and outputting a distributed representation of each token. Due to the sequential nature of RNNs, inference time is linearly dependent on the input length, and all inputs are read regardless of their importance. Efforts to…
Model captures system input variations in latent space for actionable dynamics.
In this paper, we present a structurally flat triangular form which is based on the extended chained form. We provide necessary and sufficient conditions for an affine input system with two inputs to be static feedback equivalent to the proposed triangular form, and thus a sufficient condition for an affine input syste…
Develops HDNNs for mixed geoscience data inputs.
Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to ask whether this compositional structure is reflected in the the inputs' learned representations. W…
The demand for fast and accurate structural analysis is becoming increasingly more prevalent with the advance of generative design and topology optimization technologies. As one step toward accelerating structural analysis, this work explores a deep learning based approach for predicting the stress fields in 2D linear …
VAIOM models financial returns using continuous input and categorical output.
Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks. In these tasks, graph pooling is a critical ingredient by which GNNs adapt to input graphs of varying size and structure. We propose a new graph pooling operation based on compressive Haar transforms -- HaarPo…
New research shows input-gradients can be manipulated without changing model's core function, challenging their use for model interpretation.
We propose PLLay, a novel topological layer for general deep learning models based on persistence landscapes, in which we can efficiently exploit the underlying topological features of the input data structure. In this work, we show differentiability with respect to layer inputs, for a general persistent homology with …
Paper develops neural network for distribution regression.
New method for robustly interpreting ML models using quantile constraints and Wasserstein projections.
To compare entities of differing types and structural components, the artificial neural network paradigm was used to cross-compare structural components between heterogeneous documents. Trainable weighted structural components were input into machine-learned activation functions of the neurons. The model was used for m…
Tackling pattern recognition problems in areas such as computer vision, bioinformatics, speech or text recognition is often done best by taking into account task-specific statistical relations between output variables. In structured prediction, this internal structure is used to predict multiple outputs simultaneously,…
A new model classifies multi-lead ECGs better than single-channel models.
The paper is devoted to the local classification of generic control-affine systems on an n-dimensional manifold with scalar input for any n>3 or with two inputs for n=4 and n=5, up to state-feedback transformations, preserving the affine structure. First using the Poincare series of moduli numbers we introduce the intr…
We consider the problem of joint modelling of metabolic signals and gene expression in systems biology applications. We propose an approach based on input-output factorial hidden Markov models and propose a structured variational inference approach to infer the structure and states of the model. We start from the class…
We outline a detection method for adversarial inputs to deep neural networks. By viewing neural network computations as graphs upon which information flows from input space to out- put distribution, we compare the differences in graphs induced by different inputs. Specifically, by applying persistent homology to these …
This paper analyzes the interpolation error of nonlinear Attention compared to linear regression.
New framework analyzes regret in guided diffusion for optimizing structured inputs.
We give a new algorithm for learning a two-layer neural network under a general class of input distributions. Assuming there is a ground-truth two-layer network where are weight matrices, represents noise, and the number of neurons in the hidden layer is no larger than the input or outp…
In adversarial attacks to machine-learning classifiers, small perturbations are added to input that is correctly classified. The perturbations yield adversarial examples, which are virtually indistinguishable from the unperturbed input, and yet are misclassified. In standard neural networks used for deep learning, atta…
PenduMAV is a 6-input omnidirectional MAV without internal forces.
New method shows fully-connected networks can learn convolutional structures from data.
The paper constructs minimizers for deep learning networks and analyzes their geometric structure.
Multimodal learning with deep Boltzmann machines (DBMs) is an generative approach to fuse multimodal inputs, and can learn the shared representation via Contrastive Divergence (CD) for classification and information retrieval tasks. However, it is a 2-fan DBM model, and cannot effectively handle multiple prediction tas…
Deep neural networks (DNNs) provide high image classification accuracy, but experience significant performance degradation when perturbation from various sources are present in the input. The lack of resilience to input perturbations makes DNN less reliable for systems interacting with physical world such as autonomous…
TOQ-Nets learn to recognize complex temporal events with varying objects and sequences.
Study on the structure of classifier boundaries in DNA sequencing.
Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present in the problem. In this work, we present an attention-based method to project i…