Search Results for author:
Found 40 papers, 21 papers with code
Error Estimation for Sketched SVD
In order to compute fast approximations to the singular value decompositions (SVD) of very large matrices, randomized sketching algorithms have become a leading approach.
Block-Biased Mamba for Long-Range Sequence Processing
We prove that these changes equip the model with a better-suited inductive bias and improve its expressiveness and stability.
Removing Watermarks with Partial Regeneration using Semantic Information
As AI-generated imagery becomes ubiquitous, invisible watermarks have emerged as a primary line of defense for copyright and provenance.
Powerformer: A Transformer with Weighted Causal Attention for Time-series Forecasting
Transformers have recently shown strong performance in time-series forecasting, but their all-to-all attention mechanism overlooks the (temporal) causal and often (temporally) local nature of data.
A Deep State Space Model for Rainfall-Runoff Simulations
The classical way of studying the rainfall-runoff processes in the water cycle relies on conceptual or physically-based hydrologic models.
Emoji Attack: A Method for Misleading Judge LLMs in Safety Risk Detection
To exploit this bias in Judge LLMs, we introduce the Emoji Attack -- a method that places emojis within tokens to increase the embedding differences between sub-tokens and their originals.
Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting
Flow matching has recently emerged as a powerful paradigm for generative modeling and has been extended to probabilistic time series forecasting in latent spaces.
Tuning Frequency Bias of State Space Models
State space models (SSMs) leverage linear, time-invariant (LTI) systems to effectively learn sequences with long-range dependencies.
Learning Physics for Unveiling Hidden Earthquake Ground Motions via Conditional Generative Modeling
Predicting high-fidelity ground motions for future earthquakes is crucial for seismic hazard assessment and infrastructure resilience.
WaveCastNet: An AI-enabled Wavefield Forecasting Framework for Earthquake Early Warning
To improve early warning, we propose a novel AI-enabled framework, WaveCastNet, for forecasting ground motions from large earthquakes.
HOPE for a Robust Parameterization of Long-memory State Space Models
To achieve state-of-the-art performance, an SSM often needs a specifically designed initialization, and the training of state matrices is on a logarithmic scale with a very small learning rate.
Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
In this work, we introduce Koopman VAE (KoVAE), a new generative framework that is based on a novel design for the model prior, and that can be optimized for either regular and irregular training data.
Robustifying State-space Models for Long Sequences via Approximate Diagonalization
An example is the structured state-space sequence (S4) layer, which uses the diagonal-plus-low-rank structure of the HiPPO initialization framework.
SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning
Super-resolution (SR) techniques aim to enhance data resolution, enabling the retrieval of finer details, and improving the overall quality and fidelity of the data representation.
Error Estimation for Random Fourier Features
Three key advantages of this approach are: (1) The error estimates are specific to the problem at hand, avoiding the pessimism of worst-case bounds.
Gated Recurrent Neural Networks with Weighted Time-Delay Feedback
In this paper, we present a novel approach to modeling long-term dependencies in sequential data by introducing a gated recurrent unit (GRU) with a weighted time-delay feedback mechanism.
Learning continuous models for continuous physics
Dynamical systems that evolve continuously over time are ubiquitous throughout science and engineering.
NoisyMix: Boosting Model Robustness to Common Corruptions
For many real-world applications, obtaining stable and robust statistical performance is more important than simply achieving state-of-the-art predictive test accuracy, and thus robustness of neural networks is an increasingly important topic.
Cluster-and-Conquer: A Framework For Time-Series Forecasting
Our framework -- which we refer to as "cluster-and-conquer" -- is highly general, allowing for any time-series forecasting and clustering method to be used in each step.
Long Expressive Memory for Sequence Modeling
We propose a novel method called Long Expressive Memory (LEM) for learning long-term sequential dependencies.
Ranked #1 on
Time Series Classification
on EigenWorms
Noisy Feature Mixup
We introduce Noisy Feature Mixup (NFM), an inexpensive yet effective method for data augmentation that combines the best of interpolation based training and noise injection schemes.
Stateful ODE-Nets using Basis Function Expansions
The recently-introduced class of ordinary differential equation networks (ODE-Nets) establishes a fruitful connection between deep learning and dynamical systems.
A Differential Geometry Perspective on Orthogonal Recurrent Models
In this work, we employ tools and insights from differential geometry to offer a novel perspective on orthogonal RNNs.
Noisy Recurrent Neural Networks
We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states.
Continuous-in-Depth Neural Networks
We first show that ResNets fail to be meaningful dynamical integrators in this richer sense.
Noise-Response Analysis of Deep Neural Networks Quantifies Robustness and Fingerprints Structural Malware
The ubiquity of deep neural networks (DNNs), cloud-based training, and transfer learning is giving rise to a new cybersecurity frontier in which unsecure DNNs have `structural malware' (i. e., compromised weights and activation pathways).
Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification
Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains.
Lipschitz Recurrent Neural Networks
Viewing recurrent neural networks (RNNs) as continuous-time dynamical systems, we propose a recurrent unit that describes the hidden state's evolution with two parts: a well-understood linear component plus a Lipschitz nonlinearity.
Error Estimation for Sketched SVD via the Bootstrap
In order to compute fast approximations to the singular value decompositions (SVD) of very large matrices, randomized sketching algorithms have become a leading approach.
Forecasting Sequential Data using Consistent Koopman Autoencoders
Recurrent neural networks are widely used on time series data, yet such models often ignore the underlying physical structures in such sequences.
Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
In addition to providing high-profile successes in computer vision and natural language processing, neural networks also provide an emerging set of techniques for scientific problems.
JumpReLU: A Retrofit Defense Strategy for Adversarial Attacks
To complement these approaches, we propose a very simple and inexpensive strategy which can be used to ``retrofit'' a previously-trained network to improve its resilience to adversarial attacks.
Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
In many applications, it is important to reconstruct a fluid flow field, or some other high-dimensional state, from limited measurements and limited data.
RetinaMatch: Efficient Template Matching of Retina Images for Teleophthalmology
To the best of our knowledge, this is the first template matching algorithm for retina images with small template images from unconstrained retinal areas.
Sparse Principal Component Analysis via Variable Projection
Sparse principal component analysis (SPCA) has emerged as a powerful technique for modern data analysis, providing improved interpretation of low-rank structures by identifying localized spatial structures in the data and disambiguating between distinct time scales.
Diffusion Maps meet Nyström
Diffusion maps are an emerging data-driven technique for non-linear dimensionality reduction, which are especially useful for the analysis of coherent structures and nonlinear embeddings of dynamical systems.
Randomized Nonnegative Matrix Factorization
Nonnegative matrix factorization (NMF) is a powerful tool for data mining.
Randomized Matrix Decompositions using R
The essential idea of probabilistic algorithms is to employ some amount of randomness in order to derive a smaller matrix from a high-dimensional data matrix.
Computation Mathematical Software Methodology
Compressed Dynamic Mode Decomposition for Background Modeling
We introduce the method of compressed dynamic mode decomposition (cDMD) for background modeling.
Randomized Low-Rank Dynamic Mode Decomposition for Motion Detection
This paper introduces a fast algorithm for randomized computation of a low-rank Dynamic Mode Decomposition (DMD) of a matrix.
