paper-with-me

홈 › Papers

Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling

2025-03-03 · Daksh Mittal, Ang Li, Tzu-Ching Yen, Daniel Guetta, Hongseok Namkoong

Autoregressive models have emerged as a powerful framework for modeling exchangeable sequences - i.i.d. observations when conditioned on some latent factor - enabling direct modeling of uncertainty from missing data (rather than a latent). Motivated by the critical role posterior inference plays as a subroutine in decision-making (e.g., active learning, bandits), we study the inferential and architectural inductive biases that are most effective for exchangeable sequence modeling. For the inference stage, we highlight a fundamental limitation of the prevalent single-step generation approach: inability to distinguish between epistemic and aleatoric uncertainty. Instead, a long line of works in Bayesian statistics advocates for multi-step autoregressive generation; we demonstrate this "correct approach" enables superior uncertainty quantification that translates into better performance on downstream decision-making tasks. This naturally leads to the next question: which architectures are best suited for multi-step inference? We identify a subtle yet important gap between recently proposed Transformer architectures for exchangeable sequences (Muller et al., 2022; Nguyen & Grover, 2022; Ye & Namkoong, 2024), and prove that they in fact cannot guarantee exchangeability despite introducing significant computational overhead. We illustrate our findings using controlled synthetic settings, demonstrating how custom architectures can significantly underperform standard causal masks, underscoring the need for new architectural innovations.

📄 PDF Abstract BibTeX arXiv:2503.01215

Code (1)

namkoong-lab/inductive-biases-exchangeable-sequence 공식 구현 pytorch

Tasks

Active LearningDecision MakingUncertainty Quantification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks

2020-01-10 · TACL 2020 1 · R. Thomas McCoy, Robert Frank, Tal Linzen

Learners that are exposed to the same training data might generalize differently due to differing inductive biases. In neural network models, inductive biases could in theory arise from any aspect of the model architectu…

Inductive Bias

Scalable Marked Point Processes for Exchangeable and Non-Exchangeable Event Sequences

2021-05-30 · Aristeidis Panos, Ioannis Kosmidis, Petros Dellaportas

We adopt the interpretability offered by a parametric, Hawkes-process-inspired conditional probability mass function for the marks and apply variational inference techniques to derive a general and scalable inferential f…

Point ProcessesVariational Inference

Inductive Biases and Variable Creation in Self-Attention Mechanisms

2021-10-19 · Benjamin L. Edelman, Surbhi Goel, Sham Kakade, Cyril Zhang

Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical an…

Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting

2023-05-30 · Andrea Cini, Danilo Mandic, Cesare Alippi

Relationships among time series can be exploited as inductive biases in learning effective forecasting models. In hierarchical time series, relationships among subsets of sequences induce hard constraints (hierarchical i…

ClusteringTime SeriesTime Series ClusteringTime Series Forecasting

Video Understanding by Design: How Datasets Shape Video Models

2025-09-11 · Lei Wang, Syuan-Hao Li, Piotr Koniusz, Yongsheng Gao arxiv

Research in video understanding has advanced rapidly, driven by increasingly diverse datasets and more powerful model architectures. While existing surveys typically organize progress by tasks, benchmarks, or model famil…