paper-with-me

홈 › Papers

Predictive Querying for Autoregressive Neural Sequence Models

2022-10-12 · Alex Boyd, Sam Showalter, Stephan Mandt, Padhraic Smyth

In reasoning about sequential events it is natural to pose probabilistic queries such as "when will event A occur next" or "what is the probability of A occurring before B", with applications in areas such as user modeling, medicine, and finance. However, with machine learning shifting towards neural autoregressive models such as RNNs and transformers, probabilistic querying has been largely restricted to simple cases such as next-event prediction. This is in part due to the fact that future querying involves marginalization over large path spaces, which is not straightforward to do efficiently in such models. In this paper we introduce a general typology for predictive queries in neural autoregressive sequence models and show that such queries can be systematically represented by sets of elementary building blocks. We leverage this typology to develop new query estimation methods based on beam search, importance sampling, and hybrids. Across four large-scale sequence datasets from different application domains, as well as for the GPT-2 language model, we demonstrate the ability to make query answering tractable for arbitrary queries in exponentially-large predictive path-spaces, and find clear differences in cost-accuracy tradeoffs between search and sampling methods.

📄 PDF Abstract BibTeX arXiv:2210.06464

Code (1)

ajboyd2/prob_seq_queries 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

G3PT: Unleash the power of Autoregressive Modeling in 3D Generation via Cross-scale Querying Transformer

2024-09-10 · Jinzhi Zhang, Feng Xiong, Mu Xu

Autoregressive transformers have revolutionized generative models in language processing and shown substantial promise in image and video generation. However, these models face significant challenges when extended to 3D …

3D GenerationVideo Generation

Who Needs Decoders? Efficient Estimation of Sequence-level Attributes

2023-05-09 · Yassir Fathullah, Puria Radmard, Adian Liusie, Mark J. F. Gales

State-of-the-art sequence-to-sequence models often require autoregressive decoding, which can be highly expensive. However, for some downstream tasks such as out-of-distribution (OOD) detection and resource allocation, t…

AttributeAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translation+3

A generative nonparametric Bayesian model for whole genomes

2021-12-01 · NeurIPS 2021 12 · Alan Amin, Eli Weinstein, Debora Marks

Generative probabilistic modeling of biological sequences has widespread existing and potential use across biology and biomedicine, particularly given advances in high-throughput sequencing, synthesis and editing. Howeve…

Density Estimationmodelparameter estimation

A generative nonparametric Bayesian model for whole genomes

2021-05-21 · NeurIPS 2021 12 · Alan Nawzad Amin, Eli N Weinstein, Debora Susan Marks

Generative probabilistic modeling of biological sequences has widespread existing and potential use across biology and biomedicine, particularly given advances in high-throughput sequencing, synthesis and editing. Howeve…

Density Estimationparameter estimation

Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies

2020-11-01 · Alexander H. Liu, Yu-An Chung, James Glass

Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed glo…

Representation Learning