Language models trained on chess board states outperform those on moves, even with causal masking.
problem Applying causal masking to spatial data for training unimodal language models.
method Trained bidirectional and causal self-attention models on both spatial (board-based) and sequential (move-based) chess data.
result Models trained on spatial board states achieve stronger playing strength than those trained on sequential data, even with causal masking.
Unified framework for ICL in causal and masked models.
problem Understanding ICL in masked language models and comparing it to causal models.
method Developed a statistical learning framework representing context by empirical measure and predicting using context and query.
result Upper bounds for masked and autoregressive objectives under Wasserstein-type regularity conditions.
New method reduces diffusion model function evaluations for discrete data.
problem High computational burden in generating samples from masked diffusion models.
method Modified causal attention mask and speculative sampling mechanism for non-factorized predictions.
result Achieved ~2x reduction in required network forward passes.
Regulating causal effects through averaged constraints fails to enforce conditional independence.
problem Enforcing conditional independence in regulatory and analytic settings.
method Formulated causal masking as a linear program and analyzed the resulting enforcement problem from both regulator and optimizer perspectives.
result Averaged-constraint optimization often violates stratum-wise requirements while satisfying the averaged one exactly, and detection requires conditional-independence tests.
LOCAL learns dynamic causal structures from time series data efficiently.
problem Challenges in discovering DAG from time series data due to dynamic nature and nonlinear interactions.
method LOCAL proposes a quasi-maximum likelihood-based score function and adaptive modules ACML and DGPL.
result LOCAL significantly outperforms existing methods in dynamic causal discovery.
Transformers predict price movements from limit order books.
problem Predicting price movements from limit order books.
method Causal convolutional network with masked self-attention.
result Significantly outperforms existing architectures on FI-2010 dataset.
CSHT predicts financial returns from news using a novel transformer model on a sphere.
problem Financial forecasting from news and sentiment.
method Granger-causal hypergraph structure, Riemannian geometry, causally masked Transformer attention.
result CSHT outperforms baselines in return prediction, regime classification, and asset ranking.
XTNet estimates complex cross-treatment effects in multi-category, multi-valued settings.
problem Challenges in estimating causal effects for multi-category, multi-valued treatments.
method Dynamic Neural Masking for capturing treatment interactions without restrictive assumptions.
result XTNet consistently outperforms state-of-the-art baselines in multi-category, multi-valued treatment effect estimation.
Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally masking high attribution features. We study the robustness of machine learning model…
Structured State-Space Duality connects SSMs to masked attention.
problem Connecting SSMs and attention mechanisms for efficient modeling.
method Formalizing and generalizing SSD from scalar-identity to diagonal state matrices.
result Diagonal SSMs match training complexity lower bounds and support richer dynamics.
StrNN uses neural network structures to learn conditional independencies.
problem Learning conditional independencies in neural networks.
method Designing masks for neural networks based on binary matrix factorization.
result StrNN improves density estimation and causal inference.
Transformer-based method for causal discovery with prior knowledge integration.
problem Complex nonlinear dependencies and spurious correlations in time series data.
method Multi-layer Transformer forecaster with gradient-based causal structure extraction and attention masking for prior knowledge integration.
result Significant improvement in causal discovery and causal lag estimation compared to state-of-the-art methods.
New principle for disentangling latent factors using sparse regularization.
problem Disentangling latent factors from complex data.
method Sparse regularization of latent mechanisms to induce disentanglement.
result Recovery of latent variables up to permutation under certain conditions.
New study finds best language model architecture and pretraining objective for zero-shot tasks.
problem Evaluating which language model architectures and pretraining objectives best enable zero-shot generalization.
method Compared three model architectures and two pretraining objectives across 170 billion tokens, with and without finetuning.
result Causal decoder-only models trained on autoregressive language modeling exhibit strongest zero-shot generalization.
Aggregated variables can mask causal effects, turning unconfounded into confounded relations.
problem Aggregated variables can mask causal effects, leading to paradoxical confounding.
method Analysis of how aggregated variables can change the definition of causality and the feasibility of causal relations.
result Macro causal relations are defined by micro states, not just aggregated variables.
New method targets relative risk heterogeneity in clinical trials.
problem Identifying treatment effects across subgroups with absolute risk differences.
method Modified causal forests using a novel node-splitting procedure based on relative risk.
result Relative risk causal forests can capture heterogeneity not detected by absolute risk methods.
Models predict probabilities of causation from limited data.
problem Estimating probabilities of causation requires unreliable or impractical experimental and observational data.
method Proposed Exact-MLP and Mask-MLP models trained on reliable subpopulations.
result Models achieve average MAEs of roughly 0.03, reducing MAE by 80%.
SKI speeds up Toeplitz Neural Networks by avoiding explicit decay bias and using frequency response.
problem Efficiently compute and update Toeplitz matrices in neural networks.
method Sparse plus low-rank decomposition, asymmetric SKI, frequency response modeling.
result Achieved significant speedup with minimal performance loss.
This paper studies the problem of learning causal structures from observational data. We reformulate the Structural Equation Model (SEM) with additive noises in a form parameterized by binary graph adjacency matrix and show that, if the original SEM is identifiable, then the binary adjacency matrix can be identified up…
FoundCause: Causal Discovery with Latent Confounders from Observational Data
problem Causal discovery from observational data
method FoundCause, an amortized causal discovery model trained on synthetic data
result FoundCause outperforms classical and amortized methods on real-world datasets
Causal trees struggle with accuracy in estimating treatment effects.
problem Estimating heterogeneous causal treatment effects using recursive decision trees.
method Adaptive recursive partitioning with and without sample splitting.
result Causal tree estimators can have uniform-norm errors decreasing more slowly than any power of the sample size.
A new method for efficient causal structure learning at scale.
problem Causal structure learning is computationally challenging at scale.
method Relaxed sparsest-permutation formulation with support-level relaxation and masked zero-fill incomplete Cholesky factorization.
result The method enables scalable comparison of candidate orderings and matches the accuracy of slower baselines.
PMI-Masking improves MLM pretraining by masking correlated spans efficiently.
problem Uniform token masking leads to inefficient and suboptimal performance in MLMs.
method PMI-Masking uses Pointwise Mutual Information to mask n-grams with high collocation.
result PMI-Masking reaches half the training time and improves performance.
Proposes a method for interpreting time-varying causal effect moderation in high-dimensional data.
problem Interpreting causal effect moderation in high-dimensional data with interpretability and avoiding false positives.
method Two-step method: 1) Selects a smaller model for linear causal effect moderation using Gaussian randomization, 2) Conditions on selection to construct a pivot for uniformly asymptotic semi-parametric inference.
result Consistently achieves valid coverage rates and shorter, bounded intervals in time-varying causal effect moderation.
Temporal Causal Prior-Data Fitted Networks (TCPFN) for industrial time series causal discovery
problem Estimating causal effects in industrial time series
method Temporal Causal Prior-Data Fitted Networks
result Zero-shot causal discovery with explicit reliability signals
New insights show Medicaid impacts on ED use vary widely, with some groups seeing significant increases.
problem Understanding the varied impacts of Medicaid on emergency department use.
method Causal machine learning methods to identify heterogeneous impacts.
result Meaningful heterogeneity in the effect of Medicaid on ED use, with a small group driving the overall effect.
Framework calculates positional influence in causal residual Transformers.
problem Understanding positional influence in causal residual Transformers.
method Adjoint-sensitivity framework for positional influence in causal residual Transformers.
result Exact evolution of adjoint-energy influence density and decomposition into residual transmission, nonlocal Volterra, and local channels.
ST-MTM models complex time series by decomposing and masking seasonal and trend components.
problem Forecasting complex time series with intricate temporal variations.
method Seasonal-Trend Decomposition with Masking and Contrastive Learning.
result ST-MTM achieves superior forecasting performance compared to existing methods.
Expands MLM by masking token positions, improving performance and convergence.
problem Improving language model performance and convergence.
method Masking token positions along with [MASK] tokens, using a fully connected classifier stage.
result Shows .3% improvement and 50% faster convergence for BERT Base with position masking.
Proposes a proportional masking strategy for better tabular data imputation.
problem Heterogeneity of tabular data disrupts uniform random masking in MAEs.
method Computes missingness statistics, generates proportional masks, uses MLP token mixing.
result Proportional masking preserves missingness distribution, improves imputation performance.
New framework estimates demand responses across multiple contexts with limited price variation.
problem Estimating heterogeneous linear price-response functions across multiple contexts with limited price variation and confounding.
method Meta-learning framework that identifies conditional mean of task-specific causal demand parameters given a subset of task-specific observables.
result Improved recovery of demand responses relative to standard transfer-learning baselines.
New analysis reveals masked self-supervised learning's effectiveness in extracting data structure.
problem Analyzing masked self-supervised learning in high-dimensional data.
method Developed precise high-dimensional analysis of masked modeling objectives.
result Identified phase transitions and structured regimes for masked self-supervised learning.
Generative models learn from unlabeled videos via object segmentation and scene modeling.
problem Learning generative models from unlabelled videos.
method Decomposed into three subtasks: motion segmentation, background and foreground modeling, and scene sampling.
result Approach allows learning models that generalize beyond occlusions and represent scenes in a modular fashion.
We consider the problem of inference in a causal generative model where the set of available observations differs between data instances. We show how combining samples drawn from the graphical model with an appropriate masking function makes it possible to train a single neural network to approximate all the correspond…
The recently proposed mask-predict decoding algorithm has narrowed the performance gap between semi-autoregressive machine translation models and the traditional left-to-right approach. We introduce a new training method for conditional masked language models, SMART, which mimics the semi-autoregressive behavior of mas…
This paper connects masked pre-training to Bayesian model selection.
problem Understanding the success of masked pre-training and its generalization.
method The paper shows masked pre-training corresponds to maximizing the marginal likelihood.
result Masked pre-training with a suitable scoring function maximizes the marginal likelihood.
Optimizes pruning masks for neural networks using probabilistic fine-tuning and PAC-Bayes bounds.
problem Improving neural network performance through adaptive pruning of weights.
method Optimizes stochastic pruning masks by minimizing expected loss, considering data-adaptive regularization and feature alignment.
result Probabilistic fine-tuning leads to improved test error over baseline methods in neural networks.
We consider the problem of selecting an optimal mask for an image manifold, i.e., choosing a subset of the pixels of the image that preserves the manifold's geometric structure present in the original data. Such masking implements a form of compressive sensing through emerging imaging sensor platforms for which the pow…
Recent object detectors use four-coordinate bounding box (bbox) regression to predict object locations. Providing additional information indicating the object positions and coordinates will improve detection performance. Thus, we propose two types of masks: a bbox mask and a bounding shape (bshape) mask, to represent t…
The paper investigates the effects of invalid action masking in policy gradient algorithms.
problem Invalid actions in policy gradient algorithms can lead to suboptimal performance.
method The paper provides theoretical justification and empirical demonstrations of the importance of invalid action masking.
result Invalid action masking is crucial as the number of invalid actions increases.
Efficiently combines autoregressive and set-based models for joint distributions.
problem Joint distributions over multiple predictions from set-based models.
method Causal autoregressive buffer that caches context and captures dependencies.
result Up to 20x faster joint sampling and density evaluation, up to 7x lower memory usage.
Improved YOLOv5 model detects mask-wearing with enhanced accuracy.
problem Detecting mask-wearing in high traffic public places.
method Improved YOLOv5l with Multi-Head Attentional Self-Convolution, Swin Transformer Block, I-CBAM module, and enhanced feature fusion.
result 1.1% improvement in mAP(0.5) and 1.3% improvement in mAP(0.5:0.95) compared to YOLOv5l.
Simplified masked diffusion models improve discrete data generation.
problem Complex model formulations and unclear relationships hinder discrete data generative modeling.
method Developed a simple and general framework for masked diffusion models.
result Models trained on OpenWebText surpass prior diffusion language models and outperform autoregressive models.
Masking diffusion outperforms other discrete diffusion models by incorporating jump times into the model.
problem Improving the performance of discrete diffusion models.
method Conditioning on the jump schedule of discrete Markov processes.
result Schedule-conditioned discrete diffusion (SCUD) models outperform classical and masking diffusion models.
A framework to explain decoder-only sequence classification models using intermediate predictions.
problem Explaining predictions of decoder-only sequence classification models.
method Progressive Inference framework with Single Pass-Progressive Inference and Multi Pass-Progressive Inference methods.
result Significantly better attributions compared to prior work on text classification tasks.
We decompose the squared price-of-risk premium into three components: intervention-stable premium, confounding wedge, and information loss.
problem Decomposing the squared price-of-risk premium into its components
method Identifying an order-three obstruction to aggregation across portfolios
result The decomposition is estimable and detectable with a permutation-calibrated screen
We develop mask iterative hard thresholding algorithms (mask IHT and mask DORE) for sparse image reconstruction of objects with known contour. The measurements follow a noisy underdetermined linear model common in the compressive sampling literature. Assuming that the contour of the object that we wish to reconstruct i…
The ConditionaL Neural Networks (CLNN) and the Masked ConditionaL Neural Networks (MCLNN) exploit the nature of multi-dimensional temporal signals. The CLNN captures the conditional temporal influence between the frames in a window and the mask in the MCLNN enforces a systematic sparseness that follows a filterbank-lik…