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.
Paper presents robust confidence sequences for means with known moment bounds and arbitrary corruption.
New flexible confidence sequences for robust statistical inference.
The paper develops a convex parameterization for robust RNNs ensuring stability and robustness.
RS-Del provides robustness for sequence classifiers against edit distance attacks.
R2T hybrid model improves robust regression for asymmetric noise.
Model improves robustness of neural network sequences without transition failures.
Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in many application settings matching subsequences (segments) instead of individual samples may bring in additional robustness to noise or local non-causal perturbations. Thi…
The -Alternator adapts to varying noise levels in sequences, improving robustness and performance.
Robust machine learning models improve DNA regulatory sequence prediction under various shifts.
This paper proposes a method for modeling event sequences with ambiguous timestamps, a time-discounting convolution. Unlike in ordinary time series, time intervals are not constant, small time-shifts have no significant effect, and inputting timestamps or time durations into a model is not effective. The criteria that …
Proposes MVG-CRPS for robust multivariate forecasting.
New techniques improve channel prediction in noisy wireless systems.
Paper optimizes statistical estimation for randomized smoothing to reduce adversarial robustness certification time.
For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition (ASR) performance under multimedia noise. On top of that, we apply a logits select…
New exact sequence links cohomology, automorphisms, and extensions of symmetric quandles.
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 …
Extends martingale transport for robust finance problems.
Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code modifications that preserve code functionality. (1) We define a powerful adversary that can…
New method improves deep learning model robustness and accuracy for long sequences.
Deep conditional generative models are developed to simultaneously learn the temporal dependencies of multiple sequences. The model is designed by introducing a three-way weight tensor to capture the multiplicative interactions between side information and sequences. The proposed model builds on the Temporal Sigmoid Be…
FIGARO generates symbolic music with fine-grained control.
The paper develops methods for causal inference from single-cell RNA sequencing data with multiple outcomes.
nTreeClus clusters categorical sequences using tree-based learners and k-mers.
Not all types of supervision signals are created equal: Different types of feedback have different costs and effects on learning. We show how self-regulation strategies that decide when to ask for which kind of feedback from a teacher (or from oneself) can be cast as a learning-to-learn problem leading to improved cost…
In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. More precisely, we interpret a large class of stochastic optimization methods as procedures that iteratively minimize a surrogate of th…
Sequence-to-sequence text-to-speech (TTS) is dominated by soft-attention-based methods. Recently, hard-attention-based methods have been proposed to prevent fatal alignment errors, but their sampling method of discrete alignment is poorly investigated. This research investigates various combinations of sampling methods…
We consider the minimization of a function defined on a Riemannian manifold accessible only through unbiased estimates of its gradients. We develop a geometric framework to transform a sequence of slowly converging iterates generated from stochastic gradient descent (SGD) on to an averaged i…
Existing imitation learning approaches often require that the complete demonstration data, including sequences of actions and states, are available. In this paper, we consider a more realistic and difficult scenario where a reinforcement learning agent only has access to the state sequences of an expert, while the expe…
Second generation sequencing technologies are being increasingly used for genetic association studies, where the main research interest is to identify sets of genetic variants that contribute to various phenotype. The phenotype can be univariate disease status, multivariate responses and even high-dimensional outcomes.…
P3BO optimizes biological sequence design by combining multiple methods.
RotRNN uses rotations to simplify long sequence modelling.
Data of practical interest - such as personal records, transaction logs, and medical histories - are sequential collections of events relevant to a particular source entity. Recent studies have attempted to link sequences that represent a common entity across data sets to allow more comprehensive statistical analyses a…
A competition increases financial transaction models' robustness against attacks.
New method improves GP uncertainty quantification for misspecified priors.
Paper improves recommendation systems by optimizing sequence of items for clicks.
Graph convolutional networks (GCNs) are powerful tools for graph-structured data. However, they have been recently shown to be vulnerable to topological attacks. To enhance adversarial robustness, we go beyond spectral graph theory to robust graph theory. By challenging the classical graph Laplacian, we propose a new c…
Uncertainty estimation is important for ensuring safety and robustness of AI systems. While most research in the area has focused on un-structured prediction tasks, limited work has investigated general uncertainty estimation approaches for structured prediction. Thus, this work aims to investigate uncertainty estimati…
Non-parametric estimators improve quickest changepoint detection under irregular sequence lengths.
The paper tackles gradual domain adaptation with manifold-constrained DRO, showing error bounds across distributions.
Robustly infers manifold density and geometry under high-dimensional noise.
Sequential data often originates from diverse domains across which statistical regularities and domain specifics exist. To specifically learn cross-domain sequence representations, we introduce disentangled state space models (DSSM) -- a class of SSM in which domain-invariant state dynamics is explicitly disentangled f…
Robust model predictive control (MPC) is a well-known control technique for model-based control with constraints and uncertainties. In classic robust tube-based MPC approaches, an open-loop control sequence is computed via periodically solving an online nominal MPC problem, which requires prior model information and fr…
Faster convergence of kernel mean embeddings using variance information.
This article explores the concepts of ocean wave multivariate multistep forecasting, reconstruction and feature selection. We introduce recurrent neural network frameworks, integrated with Bayesian hyperparameter optimization and Elastic Net methods. We consider both short- and long-term forecasts and reconstruction, f…
Robust feature-weighted jump models for time-dependent clustering
The paper provides robustness guarantees for mode estimation in bandits.
Method learns optimal treatment sequences from observational data.
Our work proves robustness of embedding schemes to discrete changes in text.