More Like this

1. Symphony in the Latent Space: Provably Integrating High-dimensional Techniques with Non-linear Machine Learning Models

   https://doi.org/10.1609/aaai.v37i9.26233  

   Wu, Qiong; Li, Jian; Liu, Zhenming; Li, Yanhua; Cucuringu, Mihai (February 2023, AAAI)

   This paper revisits building machine learning algorithms that involve interactions between entities, such as those between financial assets in an actively managed portfolio, or interactions between users in a social network. Our goal is to forecast the future evolution of ensembles of multivariate time series in such applications (e.g., the future return of a financial asset or the future popularity of a Twitter account). Designing ML algorithms for such systems requires addressing the challenges of high-dimensional interactions and non-linearity. Existing approaches usually adopt an ad-hoc approach to integrating high-dimensional techniques into non-linear models and re- cent studies have shown these approaches have questionable efficacy in time-evolving interacting systems. To this end, we propose a novel framework, which we dub as the additive influence model. Under our modeling assump- tion, we show that it is possible to decouple the learning of high-dimensional interactions from the learning of non-linear feature interactions. To learn the high-dimensional interac- tions, we leverage kernel-based techniques, with provable guarantees, to embed the entities in a low-dimensional latent space. To learn the non-linear feature-response interactions, we generalize prominent machine learning techniques, includ- ing designing a new statistically sound non-parametric method and an ensemble learning algorithm optimized for vector re- gressions. Extensive experiments on two common applica- tions demonstrate that our new algorithms deliver significantly stronger forecasting power compared to standard and recently proposed methods. 

   more » « less
2. Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks

   Collins, L; Hassani, H; Soltanolkotabi, M; Mokhtari, A; Shakkottai, S (June 2024, National Library of Medicine catalog)

   An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong downstream performance in a variety of contexts, demonstrating that multitask pretraining leads to effective feature learning. Although several recent theoretical studies have shown that shallow NNs learn meaningful features when either (i) they are trained on a single task or (ii) they are linear, very little is known about the closer-to-practice case of nonlinear NNs trained on multiple tasks. In this work, we present the first results proving that feature learning occurs during training with a nonlinear model on multiple tasks. Our key insight is that multi-task pretraining induces a pseudo-contrastive loss that favors representations that align points that typically have the same label across tasks. Using this observation, we show that when the tasks are binary classification tasks with labels depending on the projection of the data onto an 𝑟-dimensional subspace within the 𝑑 ≫𝑟-dimensional input space, a simple gradient-based multitask learning algorithm on a two-layer ReLU NN recovers this projection, allowing for generalization to downstream tasks with sample and neuron complexity independent of 𝑑. In contrast, we show that with high probability over the draw of a single task, training on this single task cannot guarantee to learn all 𝑟 ground-truth features. 

   more » « less
3. Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks

   Collins, Liam; Hassani, Hamed; Soltanolkotabi, Mahdi; Mokhtari, Aryan; Shakkottai, Sanjay (July 2024, Proceedings of International Conference on Machine Learning Research (ICML))

   An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong downstream performance in a variety of contexts, demonstrating that multitask pretraining leads to effective feature learning. Although several recent theoretical studies have shown that shallow NNs learn meaningful features when either (i) they are trained on a single task or (ii) they are linear, very little is known about the closer-to-practice case of nonlinear NNs trained on multiple tasks. In this work, we present the first results proving that feature learning occurs during training with a nonlinear model on multiple tasks. Our key insight is that multi-task pretraining induces a pseudo-contrastive loss that favors representations that align points that typically have the same label across tasks. Using this observation, we show that when the tasks are binary classification tasks with labels depending on the projection of the data onto an r-dimensional subspace within the d k r-dimensional input space, a simple gradient-based multitask learning algorithm on a two-layer ReLU NN recovers this projection, allowing for generalization to downstream tasks with sample and neuron complexity independent of d. In contrast, we show that with high probability over the draw of a single task, training on this single task cannot guarantee to learn all r ground-truth features. 

   more » « less
4. Feature-Function Curvature Analysis: A Geometric Framework for Explaining Differentiable Models

   Najafi, Hamed; Luo, Dongsheng; Liu, Jason (October 2025, arXiv preprint: https://doi.org/10.48550/arXiv.2510.27207)

   Explainable AI (XAI) is critical for building trust in complex machine learning models, yet mainstream attribution methods often provide an incomplete, static picture of a model's final state. By collapsing a feature's role into a single score, they are confounded by non-linearity and interactions. To address this, we introduce Feature-Function Curvature Analysis (FFCA), a novel framework that analyzes the geometry of a model's learned function. FFCA produces a 4-dimensional signature for each feature, quantifying its: (1) Impact, (2) Volatility, (3) Non-linearity, and (4) Interaction. Crucially, we extend this framework into Dynamic Archetype Analysis, which tracks the evolution of these signatures throughout the training process. This temporal view moves beyond explaining what a model learned to revealing how it learns. We provide the first direct, empirical evidence of hierarchical learning, showing that models consistently learn simple linear effects before complex interactions. Furthermore, this dynamic analysis provides novel, practical diagnostics for identifying insufficient model capacity and predicting the onset of overfitting. Our comprehensive experiments demonstrate that FFCA, through its static and dynamic components, provides the essential geometric context that transforms model explanation from simple quantification to a nuanced, trustworthy analysis of the entire learning process. 

   more » « less
5. LIT-LVM: Structured Regularization for Interaction Terms in Linear Predictors using Latent Variable Models

   Nemati, Mohammadreza; Huang, Zhipeng; Xu, Kevin S (September 2025, Transactions on machine learning research)

   Some of the simplest, yet most frequently used predictors in statistics and machine learning use weighted linear combinations of features. Such linear predictors can model non-linear relationships between features by adding interaction terms corresponding to the products of all pairs of features. We consider the problem of accurately estimating coefficients for interaction terms in linear predictors. We hypothesize that the coefficients for different interaction terms have an approximate low-dimensional structure and represent each feature by a latent vector in a low-dimensional space. This low-dimensional representation can be viewed as a structured regularization approach that further mitigates overfitting in high-dimensional settings beyond standard regularizers such as the lasso and elastic net. We demonstrate that our approach, called LIT-LVM, achieves superior prediction accuracy compared to the elastic net, hierarchical lasso, and factorization machines on a wide variety of simulated and real data, particularly when the number of interaction terms is high compared to the number of samples. LIT-LVM also provides low-dimensional latent representations for features that are useful for visualizing and analyzing their relationships. 

   more » « less