This research explores various sampling methods and probability distributions for hard alignment in sequence-to-sequence TTS synthesis.
problem Improving alignment accuracy in sequence-to-sequence text-to-speech synthesis.
method Investigated various sampling methods (greedy, beam, random) and probability distributions (Bernoulli, Concrete) for hard alignment.
result Deterministic search is more preferable than stochastic search for natural alignment transition.
Study Thompson Sampling in adversarial bit prediction, finding regret bounds and optimal sequences.
problem Adversarial bit prediction with varying error weights.
method Thompson Sampling, analyzing sequences with largest and smallest regret.
result Regret bounds for adversarial bit prediction sequences, including optimal and worst-case scenarios.
A novel sequence-to-sequence model predicts missing sensor data.
problem Missing sensor data in sequences.
method Formulated a novel sequence-to-sequence model using forward and backward RNNs.
result The model produces the lowest errors in 12% more cases than the current state-of-the-art.
A new method samples sequences without replacement using Gumbel-Top-k trick.
problem Sampling sequences without replacement from large domains efficiently.
method Gumbel-Top-k trick applied to Stochastic Beam Search.
result Efficient sampling with linear model evaluations in k k k . Paper proposes a new pipeline for few-shot classification using forget-update module and channel vector sequence.
problem Few-shot classification with limited support samples.
method Channel vector sequence construction module and forget-update module.
result Pipeline achieves state-of-the-art results on various datasets.
The paper establishes conditions for optimal sampling configurations on complex manifolds.
problem Finding optimal sampling configurations on complex manifolds.
method Analyzes point configurations on compact complex manifolds using tensor powers of Hermitian ample line bundles.
result Necessary and sufficient conditions for the existence of asymptotically Fekete sequences.
LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.
problem Optimizing large, complex design spaces is infeasible and unnecessary.
method LES uses Bayesian optimization to target solutions reachable by iterative optimizers.
result LES achieves strong sample efficiency compared to existing methods.
SRS improves deep learning accuracy on small image datasets.
problem Training deep neural networks with limited images per class.
method Fixed sequence index sampling with batch replacement.
result Significantly improved classification accuracy on CIFAR-100.
LMC improves sampling from complex distributions using quasi-random sequences.
problem Sampling from complex high-dimensional distributions with high accuracy.
method Using completely uniformly distributed (CUD) sequences in Langevin Monte Carlo (LMC) to generate Gaussian perturbations.
result LMC with low-discrepancy CUD sequences achieves smaller estimation error than standard LMC.
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…
SequenceR uses seq-to-seq learning to fix bugs in code.
problem Fixing bugs in code using machine learning.
method Sequence-to-sequence learning with copy mechanism, trained on curated code samples.
result SequenceR can perfectly predict and find correct patches for bugs.
Paper analyzes distributed learning with non-i.i.d. samples.
problem Learning rate analysis for distributed kernel ridge regression with dependent samples.
method Integral operator approach and covariance inequality for strong mixing sequences.
result Derives optimal learning rates for distributed kernel ridge regression.
k-Nearest Neighbors is one of the most fundamental but effective classification models. In this paper, we propose two families of models built on a sequence to sequence model and a memory network model to mimic the k-Nearest Neighbors model, which generate a sequence of labels, a sequence of out-of-sample feature vecto…
Recurrent models can produce infinite sequences, causing bias; new methods prevent this.
problem Inconsistency in decoding infinite-length sequences from recurrent language models.
method Defined and proved inconsistency of common decoding algorithms; proposed remedies.
result Proposed methods prevent inconsistency in practice.
Improves NMT by sampling context from predicted sequence during training.
problem Error accumulation and overcorrection in NMT due to mismatched training and inference contexts.
method Samples context words from both ground truth and predicted sequences during training.
result Significant improvements on multiple datasets, including Chinese->English and WMT'14 English->German.
Introduces alternators for modeling sequences, outperforming baselines.
problem Modeling complex sequential data with stability and efficiency.
method Two neural networks (OTN and FTN) alternate between outputting samples in observation and feature spaces, learned via cross-entropy criterion.
result Alternators outperform strong baselines in various domains (Lorenz equations, Neuroscience, Climate Science).
The paper introduces methods to quantify uncertainty in sampling without replacement.
problem Accurately estimating parameters from finite populations sampled without replacement.
method Develops confidence sequences using Bayesian and empirical methods.
result Improved confidence intervals and sequences for sampling without replacement.
A new method optimizes neural sequence models for better task performance.
problem Training neural sequence models with maximum likelihood estimation ignores task losses.
method Maximum likelihood guided parameter search (MGS) in the parameter space.
result MGS optimizes sequence-level losses, reducing repetition and non-termination.
For autonomous agents to successfully operate in the real world, anticipation of future events and states of their environment is a key competence. This problem has been formalized as a sequence extrapolation problem, where a number of observations are used to predict the sequence into the future. Real-world scenarios …
Tensor networks improve sequence modeling with efficient sampling and parallelism.
problem Efficient probabilistic modeling of sequence data.
method Uniform matrix product state (u-MPS) model for sequence data.
result u-MPS enable efficient sampling and parallel evaluation of sequences.
The study compares different scRNA sequencing methods using a high-dimensional dataset.
problem To identify unique characteristics of different scRNA sequencing methods.
method Quantitative comparison through clustering analysis of a high-dimensional dataset.
result Identifies unique characteristics associated with different scRNA sequencing methods.
Transformers can outperform feedforward and recurrent networks due to dynamic sparsity.
problem Understanding when and why Transformers outperform other neural network architectures.
method Analyzing a sequence-to-sequence data generating model with dynamic sparsity, proving sample complexity differences between feedforward, recurrent, and Transformers.
result Transformers can learn dynamic sparsity models with lower sample complexity than feedforward and recurrent networks.
This paper uses bandit theory and Thompson Sampling to optimize protein sequences.
problem Optimizing protein sequences using machine learning and directed evolution.
method Proposes a Thompson Sampling-guided Directed Evolution (TS-DE) framework.
result TS-DE achieves a nearly optimal Bayesian regret of order i l d e O ( d 2 M T ) ilde O(d^{2}\sqrt{MT}) i l d e O ( d 2 M T ) . Study reveals how machine translation models can leak data privacy.
problem Detecting if a specific data sample was used to train machine translation models.
method Defined membership inference problem for sequence-to-sequence models, tested on machine translation models.
result Machine translation models can leak private information about training data.
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 …
A new neural sequence prediction method using error-correcting codes improves accuracy and convergence.
problem Improving neural sequence prediction accuracy and speed.
method Error-correcting output codes, separable code maximization, latent variable mixture sampling.
result Consistent improvements on language modeling datasets and text generation tasks.
P3BO optimizes biological sequence design by combining multiple methods.
problem Variability in performance of black-box optimization methods for biological sequence design.
method Population-Based Black-Box Optimization (P3BO) that samples sequences from an ensemble of methods, weighting by past performance.
result P3BO outperforms individual methods, proposing higher quality and more diverse sequences.
Training-free method improves large language model sequence quality via reward-guided sampling.
problem Optimizing large language model sequence quality over token likelihood.
method Reward-augmented target distribution combined with Sequential Monte Carlo sampling.
result Significant gains in sequence generation and mathematical reasoning tasks.
Paper shows how online betting algorithms' regret can be used to create tight confidence sequences.
problem Estimating the expectation of random variables from samples and creating time-uniform confidence sequences.
method Converts the regret guarantee of universal portfolio algorithms into time-uniform concentration inequalities and confidence sequences.
result Numerically obtained confidence sequences are never vacuous and satisfy the law of iterated logarithm.
A new method for prioritizing sequences in reinforcement learning improves learning efficiency.
problem Efficient learning in reinforcement learning algorithms.
method Prioritized Sequence Experience Replay (PSER) for prioritizing sequences of experience.
result PSER is guaranteed to converge faster than PER and substantially improves performance.
We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorithm which samples valid extensions and an approximate decoding algorithm. We experiment with the Wall …
We study a variant of the source identification game with training data in which part of the training data is corrupted by an attacker. In the addressed scenario, the defender aims at deciding whether a test sequence has been drawn according to a discrete memoryless source X ∼ P X X \sim P_X X ∼ P X , whose statistics are known to hi…
Time-aware neural models improve system identification from unevenly sampled data.
problem Improving system identification from continuous variables with unevenly sampled time data.
method Introduced a time-aware and stationary extension of recurrent neural networks.
result Demonstrated improved performance on industrial input/output processes.
Impute missing events in continuous-time sequences using particle smoothing.
problem Missing events in continuous-time sequences.
method Particle smoothing with trainable bidirectional LSTM proposals.
result Imputed sequences have low Bayes risk compared to ground truth.
Theoretical analysis shows MDMs can be efficient but not for all metrics.
problem Understanding the efficiency-accuracy trade-off of diffusion language models.
method Theoretical analysis of Masked Diffusion Model (MDM) using perplexity and sequence error rate as metrics.
result MDM achieves near-optimal perplexity but requires linear scaling for sequence error rate, highlighting efficiency-accuracy trade-offs.
An unsupervised anomaly detection method for irregularly sampled time-series data.
problem Anomaly detection in irregularly sampled or missing valued time-series data.
method Uses LSTM networks with time modulation gates to extract temporal features and SVDD for anomaly labeling.
result Significantly outperforms standard approaches on real-life datasets.
Efficiently samples sequences without replacement for machine learning models.
problem Generating diverse outputs from sequential models without duplicates.
method Incremental sampling procedure for randomized programs, including neural models.
result Efficacy and flexibility of incremental sampling for large output spaces.
A faster method for optimizing DNA and protein sequences using machine learning.
problem Designing DNA and protein sequences with improved function.
method Activation maximization with a straight-through approximation and adaptive entropy variable.
result Fast SeqProp achieves up to 100-fold faster convergence and improved fitness optima.
Adversarial learning for mixture Hawkes processes improves performance.
problem Learning mixture models of Hawkes processes from event sequences.
method Iterative self-paced learning with adversarial self-paced mechanism.
result The proposed method outperforms traditional methods consistently.
Machine learning accurately diagnoses cancer from whole genome sequencing data.
problem Accurate cancer diagnosis at all stages.
method Novel MLAC (Machine Learning Against Cancer) method using next-gen RNA sequencing.
result Perfect precision, sensitivity, and specificity achieved for most tumor types.
Alternative sampling method for autoregressive models using Langevin dynamics.
problem Efficiently sampling from autoregressive models.
method Initialize sequences with white noise and follow Langevin dynamics on global log-likelihood.
result Parallelizes and generalizes sampling process for autoregressive models.
Near-optimal confidence intervals for bounded data.
problem Online inference for sequential decision problems like A/B testing.
method Utilizing Bentkus' concentration results to improve on existing methods.
result Near-optimal confidence intervals confirmed favorable in synthetic and practical applications.
A nonparametric anomalous hypothesis testing problem is investigated, in which there are totally n sequences with s anomalous sequences to be detected. Each typical sequence contains m independent and identically distributed (i.i.d.) samples drawn from a distribution p, whereas each anomalous sequence contains m i.i.d.…
The problem of universal outlying sequence detection is studied, where the goal is to detect outlying sequences among M M M sequences of samples. A sequence is considered as outlying if the observations therein are generated by a distribution different from those generating the observations in the majority of the sequenc…
Efficient inference method for adaptive experiments with tighter confidence sequences.
problem Efficient inference of Average Treatment Effect in a changing policy sequential experiment.
method Semiparametric efficient inference using Adaptive Augmented Inverse-Probability Weighted estimator and asymptotic confidence sequences.
result Derives tighter confidence sequences for adaptive experiments under data-dependent stopping times.
Black-box attacks on RL agents using temporal information.
problem Vulnerability of RL agents to adversarial samples.
method Sequence-to-sequence models for predicting future actions.
result Adversarial samples can trigger RL agents to misbehave after a delay.
OptiGAN uses GAN and RL to optimize sequence generation for specific goals.
problem Challenging in sequence generation tasks to generate sequences with specific desired goals.
method Integrates GAN and RL to optimize desired goal scores using policy gradients.
result Achieves higher desired scores in text and real-valued sequence generation.
Differentiable sampling corrects alignment issues in neural machine translation.
problem Incorrect alignment of reference words and sampled output in scheduled sampling.
method Optimizes alignment probability based on model's soft alignment prediction.
result Improves BLEU score compared to maximum likelihood and scheduled sampling.