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.
Sequence probability predicts correctness in LLMs, but not for repeated prompts
In many applications, accurate class probability estimates are required, but many types of models produce poor quality probability estimates despite achieving acceptable classification accuracy. Even though probability calibration has been a hot topic of research in recent times, the majority of this has investigated n…
For a sequence of nonnegative random variables, we provide simple necessary and sufficient conditions to ensure that each sequence of its forward convex combinations converges in probability to the same limit. These conditions correspond to an essentially measure-free version of the notion of uniform integrability.
Segmental structure is a common pattern in many types of sequences such as phrases in human languages. In this paper, we present a probabilistic model for sequences via their segmentations. The probability of a segmented sequence is calculated as the product of the probabilities of all its segments, where each segment …
Sequences have become first class citizens in supervised learning thanks to the resurgence of recurrent neural networks. Many complex tasks that require mapping from or to a sequence of observations can now be formulated with the sequence-to-sequence (seq2seq) framework which employs the chain rule to efficiently repre…
This paper establishes for the first time the predictive performance of speed priors and their computational complexity. A speed prior is essentially a probability distribution that puts low probability on strings that are not efficiently computable. We propose a variant to the original speed prior (Schmidhuber, 2002),…
Paper examines trade/no trade patterns in illiquid stocks, highlighting effects of varying zero returns probabilities.
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…
Video sequences contain rich dynamic patterns, such as dynamic texture patterns that exhibit stationarity in the temporal domain, and action patterns that are non-stationary in either spatial or temporal domain. We show that a spatial-temporal generative ConvNet can be used to model and synthesize dynamic patterns. The…
Hidden Markov models (HMMs) are one of the most widely used statistical methods for analyzing sequence data. However, the reporting of output from HMMs has largely been restricted to the presentation of the most-probable (MAP) hidden state sequence, found via the Viterbi algorithm, or the sequence of most probable marg…
Price movements of stock market are not totally random. In fact, what drives the financial market and what pattern financial time series follows have long been the interest that attracts economists, mathematicians and most recently computer scientists [17]. This paper gives an idea about the trend analysis of stock mar…
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of t…
While neural sequence generation models achieve initial success for many NLP applications, the canonical decoding procedure with left-to-right generation order (i.e., autoregressive) in one-pass can not reflect the true nature of human revising a sentence to obtain a refined result. In this work, we propose XL-Editor, …
Transformers can simulate MLE for Bayesian network sequences.
This paper examines how different decoding algorithms for LLMs align with various goals.
Paper optimizes change-point detection using learned distributions from training sequences.
We obtain an index of the complexity of a random sequence by allowing the role of the measure in classical probability theory to be played by a function we call the generating mechanism. Typically, this generating mechanism will be a finite automata. We generate a set of biased sequences by applying a finite state auto…
Stratifying patients at risk for postoperative complications may facilitate timely and accurate workups and reduce the burden of adverse events on patients and the health system. Currently, a widely-used surgical risk calculator created by the American College of Surgeons, NSQIP, uses 21 preoperative covariates to asse…
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…
A Semi-Hidden Markov Model (SHMM) for bursty error channels is defined by a state transition probability matrix , a prior probability vector , and the state dependent output symbol error probability matrix . Several processes are utilized for estimating , and from a given empirically obtained or sim…
New attention model removes softmax, improving sequence length bias.
Paper explores learning patterns in binary sequences, finding no method consistently outperforms others.
A measure called relative cluster entropy distinguishes between correlated and uncorrelated sequences.
This paper studies clustering of data sequences using the k-medoids algorithm. All the data sequences are assumed to be generated from \emph{unknown} continuous distributions, which form clusters with each cluster containing a composite set of closely located distributions (based on a certain distance metric between di…
Expands Hidden Markov Model to include Markov chain observations.
Investigates probability of error in structured thresholding bandit problems.
Constrained sequence codes have been widely used in modern communication and data storage systems. Sequences encoded with constrained sequence codes satisfy constraints imposed by the physical channel, hence enabling efficient and reliable transmission of coded symbols. Traditional encoding and decoding of constrained …
Develops confidence bounds for off-policy evaluation in contextual bandits.
The paper estimates variance of random sections on complex manifolds.
Study on continuous sequence classification with distribution uncertainty.
Introduces hierarchical uncertainty using U-sequences.
We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance. OCD is efficient, has no hyper-parameters of its own, and does not require pretraining or joint optimization with conditional log-likelihood. Given a partial sequence generated by th…
Predicts cryptocurrency pump probability using sequence-based neural networks.
Deep learning detects novel changes in time series data.
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…
Develops effective adversarial attacks on probabilistic forecasting models.
Deep learning techniques have been hugely successful for traditional supervised and unsupervised machine learning problems. In large part, these techniques solve continuous optimization problems. Recently however, discrete generative deep learning models have been successfully used to efficiently search high-dimensiona…
A novel transformer model improves classification of partially ordered sequences.
The problem is sequence prediction in the following setting. A sequence x1,..., xn,... of discrete-valued observations is generated according to some unknown probabilistic law (measure) mu. After observing each outcome, it is required to give the conditional probabilities of the next observation. The measure mu belongs…
LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.
IAE extracts innovations sequences for non-Gaussian processes.
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…
Bayesian sequence prediction is a simple technique for predicting future symbols sampled from an unknown measure on infinite sequences over a countable alphabet. While strong bounds on the expected cumulative error are known, there are only limited results on the distribution of this error. We prove tight high-probabil…
Sequence models assign probabilities to variable-length sequences such as natural language texts. The ability of sequence models to capture temporal dependence can be characterized by the temporal scaling of correlation and mutual information. In this paper, we study the mutual information of recurrent neural networks …
Framework handles both exchangeable and non-exchangeable event sequences without tuning.
Estimates stationary mass and frequency from non-i.i.d. data.
The paper provides bounds for LSA with fixed stepsizes under random estimates.
Paper develops probabilistic bounds for a stochastic gradient algorithm in non-convex problems.