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.
Bidirectional attention is shown to be equivalent to a continuous bag of words model with mixture-of-experts.
TimeVQVAE uses VQ for better time series generation.
Research uses SWT and BDLSTM to forecast stock and oil prices amid COVID-19.
Recent work has shown that topological enhancements to recurrent neural networks (RNNs) can increase their expressiveness and representational capacity. Two popular enhancements are stacked RNNs, which increases the capacity for learning non-linear functions, and bidirectional processing, which exploits acausal informa…
New theory explains signal propagation in normalization-free transformers.
Bidirectional VAE reduces parameters and improves image tasks.
We propose a neural architecture with the main characteristics of the most successful neural models of the last years: bidirectional RNNs, encoder-decoder, and the Transformer model. Evaluation on three sequence labelling tasks yields results that are close to the state-of-the-art for all tasks and better than it for s…
New bidirectional model predicts magnetohydrodynamics fields and estimates uncertainty.
Sharp error bounds derived for bidirectional GANs without restrictive assumptions.
Sketch-BERT learns vector sketches using BERT-like self-supervised learning.
Chatbot uses BERT to handle financial investment questions, improving accuracy and decision-making.
This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer model described in Dehghani et al. (2018). We further improve this model by addin…
Enhanced decision-making through Dreamer's anticipatory trajectories and Online Decision Transformer.
We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model. We show that there is shared structure between different NLP datasets that HUBERT, but not BERT, is able to learn and leverage. We validate …
Self-supervised bidirectional transformer models such as BERT have led to dramatic improvements in a wide variety of textual classification tasks. The modern digital world is increasingly multimodal, however, and textual information is often accompanied by other modalities such as images. We introduce a supervised mult…
Neural sequence generation is typically performed token-by-token and left-to-right. Whenever a token is generated only previously produced tokens are taken into consideration. In contrast, for problems such as sequence classification, bidirectional attention, which takes both past and future tokens into consideration, …
New method estimates bidirectional causal effects in large-scale systems.
Bidirectional LSTM predicts seizures with 84% accuracy.
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense method, Featurized Bidirectional Generative Adversarial Networks (FBGAN), to extract the semantic feature…
Study compares BERT with other sentiment analysis models.
Paper proposes using LSTM for LSH-based sequence alignment.
Framework learns sentence order from paragraphs using attention and transformer networks.
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…
Bidirectional bounds stabilize training of energy-based models.
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…
BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.
Paper proposes BMPO to optimize policies using bidirectional models.
We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing successful architectures that improves sample efficiency. We aim to address the limitation of current network transformation operations that…
New method for bidirectional generative modeling using adversarial gradient estimation.
Bi-Mamba model predicts diffusion coefficients and exponents from short data.
SKI speeds up Toeplitz Neural Networks by avoiding explicit decay bias and using frequency response.
Paper improves communication in distributed optimization, reducing worker-to-server data exchanges.
DBGAN learns graph node representations by balancing distribution consistency.
ICP improves text infilling and POS tagging with valid confidence sets.
We consider the problem of training input-output recurrent neural networks (RNN) for sequence labeling tasks. We propose a novel spectral approach for learning the network parameters. It is based on decomposition of the cross-moment tensor between the output and a non-linear transformation of the input, based on score …
Artemis framework improves distributed learning with bidirectional compression and partial participation.
Paper proposes a hybrid MTL framework for improved stock market prediction accuracy.
A fundamental problem in geophysical modeling is related to the identification and approximation of causal structures among physical processes. However, resolving the bidirectional mappings between physical parameters and model state variables (i.e., solving the forward and inverse problems) is challenging, especially …
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We…
e-Yantra Robotics Competition (eYRC) is a unique Robotics Competition hosted by IIT Bombay that is actually an Embedded Systems and Robotics MOOC. Registrations have been growing exponentially in each year from 4500 in 2012 to over 34000 in 2019. In this 5-month long competition students learn complex skills under seve…
In this work we introduce a novel approach to train Bidirectional Generative Adversarial Model (BiGAN) in a semi-supervised manner. The presented method utilizes triplet loss function as an additional component of the objective function used to train discriminative data representation in the latent space of the BiGAN m…
Objective: The aim of this study is to develop an automated classification algorithm for polysomnography (PSG) recordings to detect non-apneic and non-hypopneic arousals. Our particular focus is on detecting the respiratory effort-related arousals (RERAs) which are very subtle respiratory events that do not meet the cr…
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora…
BERT models outperform GPT in financial engineering sentiment analysis.
SAMBA predicts stock returns efficiently using Mamba and graph neural networks.
Recurrent neural networks have become ubiquitous in computing representations of sequential data, especially textual data in natural language processing. In particular, Bidirectional LSTMs are at the heart of several neural models achieving state-of-the-art performance in a wide variety of tasks in NLP. However, BiLSTM…
Improved DeepONet variants using Transformer cross-conditioning enhance PDE solution efficiency.
Paper analyzes and compares ELF algorithms for federated learning.