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.
Decouples critic chunk length from policy to improve policy reactivity and performance.
A quantum model classifies financial sentiment by mapping text chunks to quantum circuits.
Q-chunking improves RL for long tasks by chunking actions.
Streamable model improves speech recognition performance.
Chunking is a significant CL problem, accounting for half of performance drop, and current methods don't address it.
Interpretable semantic textual similarity (iSTS) task adds a crucial explanatory layer to pairwise sentence similarity. We address various components of this task: chunk level semantic alignment along with assignment of similarity type and score for aligned chunks with a novel system presented in this paper. We propose…
Recently, Transformer has gained success in automatic speech recognition (ASR) field. However, it is challenging to deploy a Transformer-based end-to-end (E2E) model for online speech recognition. In this paper, we propose the Transformer-based online CTC/attention E2E ASR architecture, which contains the chunk self-at…
Action chunking and data exploration improve behavior cloning in robotics.
Linear algebra algorithms are used widely in a variety of domains, e.g machine learning, numerical physics and video games graphics. For all these applications, loop-level parallelism is required to achieve high performance. However, finding the optimal way to schedule the workload between threads is a non-trivial prob…
Ricci-Filtration enhances retrieval-augmented generation rerankers for query-answer tasks by using discrete Ricci flow on graphs.
This paper improves retrieval for LLMs in financial document Q&A.
TMTF improves time series visualization by separating dynamic regimes.
CMoS improves time series forecasting with minimal parameters.
SDCOR clusters massive datasets efficiently, detecting outliers with low memory usage.
FinFlowRL combines imitation and reinforcement learning for better financial control.
ReWTS ensemble improves time-series forecasting by adapting to changing dynamics.
UIClust efficiently clusters data streams with concept drift detection.
Framework for lifelong learning of compositional structures.
KATA improves associative recall by optimizing feature maps derived from nonnegative attention weights.
Reinforcement learning has attracted great attention recently, especially policy gradient algorithms, which have been demonstrated on challenging decision making and control tasks. In this paper, we propose an active multi-step TD algorithm with adaptive stepsizes to learn actor and critic. Specifically, our model cons…
Recent studies have shown that neural models can achieve high performance on several sequence labelling/tagging problems without the explicit use of linguistic features such as part-of-speech (POS) tags. These models are trained only using the character-level and the word embedding vectors as inputs. Others have shown …
Although support vector machines (SVMs) are theoretically well understood, their underlying optimization problem becomes very expensive, if, for example, hundreds of thousands of samples and a non-linear kernel are considered. Several approaches have been proposed in the past to address this serious limitation. In this…
Improved speech enhancement with MNTFA using time-frequency attention.
A new framework uses directed information to efficiently select context chunks.
Incremental clustering approaches have been proposed for handling large data when given data set is too large to be stored. The key idea of these approaches is to find representatives to represent each cluster in each data chunk and final data analysis is carried out based on those identified representatives from all t…
One of the limiting factors of using support vector machines (SVMs) in large scale applications are their super-linear computational requirements in terms of the number of training samples. To address this issue, several approaches that train SVMs on many small chunks of large data sets separately have been proposed in…
FinReflectKG - EvalBench benchmarks financial KG extraction from SEC 10-K filings.
Inspired by the hierarchical hidden Markov models (HHMM), we present the hierarchical semi-Markov conditional random field (HSCRF), a generalisation of embedded undirectedMarkov chains tomodel complex hierarchical, nestedMarkov processes. It is parameterised in a discriminative framework and has polynomial time algorit…
Conditional random fields (CRFs) have been shown to be one of the most successful approaches to sequence labeling. Various linear-chain neural CRFs (NCRFs) are developed to implement the non-linear node potentials in CRFs, but still keeping the linear-chain hidden structure. In this paper, we propose NCRF transducers, …
Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this paper, we present a novel framework for introducing declarative knowledge to ne…
stream-learn is a Python package compatible with scikit-learn and developed for the drifting and imbalanced data stream analysis. Its main component is a stream generator, which allows to produce a synthetic data stream that may incorporate each of the three main concept drift types (i.e. sudden, gradual and incrementa…
Bayesian Neural Networks detect gravitational wave events with high accuracy and real-time potential.
Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To address these issues, we propose Monotonic Chunkwise Attention (MoChA), which adaptiv…
FinFlowRL learns from experts to optimize financial control in changing markets.
Named entity recognition (NER) plays an important role in text-based information retrieval. In this paper, we combine Bidirectional Long Short-Term Memory (Bi-LSTM) \cite{hochreiter1997,schuster1997} with Conditional Random Field (CRF) \cite{lafferty2001} to create a novel deep learning model for the NER problem. Each …
For some , let be a finite index subgroup of the mapping class group of a genus surface (possibly with boundary components and punctures). An old conjecture of Ivanov says that the abelianization of should be finite. In this note, we prove two theorems supporting this conjecture. For the first, le…
Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations …
TAWT improves cross-task learning efficiency and guarantees.
Many modern applications deal with multi-label data, such as functional categorizations of genes, image labeling and text categorization. Classification of such data with a large number of labels and latent dependencies among them is a challenging task, and it becomes even more challenging when the data is received onl…
We propose a two-sample testing procedure based on learned deep neural network representations. To this end, we define two test statistics that perform an asymptotic location test on data samples mapped onto a hidden layer. The tests are consistent and asymptotically control the type-1 error rate. Their test statistics…
BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its major limitations - applicability to inputs longer than a few hundred words, such as…
A key aspect of Federated Learning (FL) is the requirement of a centralized aggregator to maintain and update the global model. However, in many cases orchestrating a centralized aggregator might be infeasible due to numerous operational constraints. In this paper, we introduce BAFFLE, an aggregator free, blockchain dr…
The restricted Boltzmann machine (RBM) is a flexible tool for modeling complex data, however there have been significant computational difficulties in using RBMs to model high-dimensional multinomial observations. In natural language processing applications, words are naturally modeled by K-ary discrete distributions, …
Diffusion models reveal latent hierarchical structure in data.
Extends NAS to learn both intra-cell and inter-cell architectures for language modeling.
Classification of sequence data is the topic of interest for dynamic Bayesian models and Recurrent Neural Networks (RNNs). While the former can explicitly model the temporal dependencies between class variables, the latter have a capability of learning representations. Several attempts have been made to improve perform…
New approach uses neural networks to learn program structure and parameters.
Given a knot in 3-space, one can associate a sequence of Laurrent polynomials, whose th term is the th colored Jones polynomial. The Generalized Volume Conjecture states that the value of the -th colored Jones polynomial at $\exp(2 πi \a/n)$ is a sequence of complex numbers that grows exponentially, for a fixe…