arXiv research

P3BO optimizes biological sequence design by combining multiple methods.

This research explores various sampling methods and probability distributions for hard alignment in sequence-to-sequence TTS synthesis.

Sequence classification is an important data mining task in many real world applications. Over the past few decades, many sequence classification methods have been proposed from different aspects. In particular, the pattern-based method is one of the most important and widely studied sequence classification methods in …

The study compares different scRNA sequencing methods using a high-dimensional dataset.

Deep learning models optimize protein sequences.

Predicts node sequences in graphs using multi-order network models.

A new method for fast graph embedding using diffusion graphs.

Researchers develop flexible kernels for biological sequences with guaranteed reliability.

This paper proposes a new meta-learning method -- named HARMLESS (HAwkes Relational Meta LEarning method for Short Sequences) for learning heterogeneous point process models from short event sequence data along with a relational network. Specifically, we propose a hierarchical Bayesian mixture Hawkes process model, whi…

TCT learns multimodal sequence representations by translating from related sequences.

ATS2S model predicts RUL of industrial equipment using attention mechanism.

Sequence feature embedding is a challenging task due to the unstructuredness of sequence, i.e., arbitrary strings of arbitrary length. Existing methods are efficient in extracting short-term dependencies but typically suffer from computation issues for the long-term. Sequence Graph Transform (SGT), a feature embedding …

A new model captures variability in time series data.

Detects outliers in continuous-time event sequences, including unexpected absences and occurrences.

Inferring the structural properties of a protein from its amino acid sequence is a challenging yet important problem in biology. Structures are not known for the vast majority of protein sequences, but structure is critical for understanding function. Existing approaches for detecting structural similarity between prot…

Sequence probability predicts correctness in LLMs, but not for repeated prompts

Develops methods to create manifolds with positive scalar curvature.

End-to-end transformer model improves lexical stress detection accuracy.

Many real-world applications require robust algorithms to learn point processes based on a type of incomplete data --- the so-called short doubly-censored (SDC) event sequences. We study this critical problem of quantitative asynchronous event sequence analysis under the framework of Hawkes processes by leveraging the …

Magnetic resonance imaging (MRI) is being increasingly utilized to assess, diagnose, and plan treatment for a variety of diseases. The ability to visualize tissue in varied contrasts in the form of MR pulse sequences in a single scan provides valuable insights to physicians, as well as enabling automated systems perfor…

nTreeClus clusters categorical sequences using tree-based learners and k-mers.

CAUSE learns Granger causality from event sequences, outperforming existing methods.

Adaptive correlated MC improves sequence generation stability.

New methods tackle adversarial attacks on categorical sequences, improving model security.

Method extracts knowledge from LSTM for sequence validation.

A faster method for optimizing DNA and protein sequences using machine learning.

For any prime power $q$ and any dimension $s$, a new construction of $(t,s)$-sequences in base $q$ using global function fields is presented. The construction yields an analog of Halton sequences for global function fields. It is the first general construction of $(t,s)$-sequences that is not based on the digital metho…

This paper is based on the paper "Locally free sheaves on complex supermanifolds" of A.L.Onishchik, E.G. Vishnyakova, where two classification theorems for locally free sheaves on supermanifolds were proved and a spectral sequence for a locally free sheaf of modules E was obtained. We consider another filtration of the…

Variational method for eigenvalues on manifolds.

A new method optimizes neural sequence models for better task performance.

Consider a general machine learning setting where the output is a set of labels or sequences. This output set is unordered and its size varies with the input. Whereas multi-label classification methods seem a natural first resort, they are not readily applicable to set-valued outputs because of the growth rate of the o…

The paper addresses probability calibration for incomplete sequences.

This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. Our method extends the BERT model for text sequences to the case of sequences of rea…

Defines spectral sequences for fiberwise Dirac operators and proves adiabatic limit formula.

Existence of an infinite sequence of harmonic maps between spheres of certain dimensions was proven by Bizon and Chmaj. This sequence shares many features of the Bartnik-McKinnon sequence of solutions to the Einstein-Yang-Mills equations as well as sequences of solutions that have arisen in other physical models. We ap…

The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form …

Hybridizes CEM and gradient descent for efficient model-predictive control.

Spacetimeformer learns spatiotemporal relationships from data alone.

We present methods for online linear optimization that take advantage of benign (as opposed to worst-case) sequences. Specifically if the sequence encountered by the learner is described well by a known "predictable process", the algorithms presented enjoy tighter bounds as compared to the typical worst case bounds. Ad…

LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.

We propose a novel adversarial learning strategy for mixture models of Hawkes processes, leveraging data augmentation techniques of Hawkes process in the framework of self-paced learning. Instead of learning a mixture model directly from a set of event sequences drawn from different Hawkes processes, the proposed metho…

PANDA predicts protein binding affinity changes from sequences, outperforming existing methods.

In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization. Through jointly attending to topics and word-level alignment, o…

New BGG sequences on manifolds help solve elasticity and relativity problems.

Improved incremental sequence classification with temporal consistency.

Events in the world may be caused by other, unobserved events. We consider sequences of events in continuous time. Given a probability model of complete sequences, we propose particle smoothing---a form of sequential importance sampling---to impute the missing events in an incomplete sequence. We develop a trainable fa…

Generation of pseudorandom numbers from different probability distributions has been studied extensively in the Monte Carlo simulation literature. Two standard generation techniques are the acceptance-rejection and inverse transformation methods. An alternative approach to Monte Carlo simulation is the quasi-Monte Carl…

Data of sequential nature arise in many application domains in forms of, e.g. textual data, DNA sequences, and software execution traces. Different research disciplines have developed methods to learn sequence models from such datasets: (i) in the machine learning field methods such as (hidden) Markov models and recurr…