More Like this

1. Wide and deep neural networks achieve consistency for classification

   https://doi.org/10.1073/pnas.2208779120  

   Radhakrishnan, Adityanarayanan; Belkin, Mikhail; Uhler, Caroline (April 2023, Proceedings of the National Academy of Sciences)

   While neural networks are used for classification tasks across domains, a long-standing open problem in machine learning is determining whether neural networks trained using standard procedures are consistent for classification, i.e., whether such models minimize the probability of misclassification for arbitrary data distributions. In this work, we identify and construct an explicit set of neural network classifiers that are consistent. Since effective neural networks in practice are typically both wide and deep, we analyze infinitely wide networks that are also infinitely deep. In particular, using the recent connection between infinitely wide neural networks and neural tangent kernels, we provide explicit activation functions that can be used to construct networks that achieve consistency. Interestingly, these activation functions are simple and easy to implement, yet differ from commonly used activations such as ReLU or sigmoid. More generally, we create a taxonomy of infinitely wide and deep networks and show that these models implement one of three well-known classifiers depending on the activation function used: 1) 1-nearest neighbor (model predictions are given by the label of the nearest training example); 2) majority vote (model predictions are given by the label of the class with the greatest representation in the training set); or 3) singular kernel classifiers (a set of classifiers containing those that achieve consistency). Our results highlight the benefit of using deep networks for classification tasks, in contrast to regression tasks, where excessive depth is harmful. 

   more » « less
2. Generalized Boosting

   Suggala, A.; Liu, B.; Ravikumar, P. (October 2020, Advances in neural information processing systems)

   Boosting is a widely used learning technique in machine learning for solving classification problems. In boosting, one predicts the label of an example using an ensemble of weak classifiers. While boosting has shown tremendous success on many classification problems involving tabular data, it performs poorly on complex classification tasks involving low-level features such as image classification tasks. This drawback stems from the fact that boosting builds an additive model of weak classifiers, each of which has very little predictive power. Often, the resulting additive models are not powerful enough to approximate the complex decision boundaries of real-world classification problems. In this work, we present a general framework for boosting where, similar to traditional boosting, we aim to boost the performance of a weak learner and transform it into a strong learner. However, unlike traditional boosting, our framework allows for more complex forms of aggregation of weak learners. In this work, we specifically focus on one form of aggregation - function composition. We show that many popular greedy algorithms for learning deep neural networks (DNNs) can be derived from our framework using function compositions for aggregation. Moreover, we identify the drawbacks of these greedy algorithms and propose new algorithms that fix these issues. Using thorough empirical evaluation, we show that our learning algorithms have superior performance over traditional additive boosting algorithms, as well as existing greedy learning techniques for DNNs. An important feature of our algorithms is that they come with strong theoretical guarantees. 

   more » « less
3. AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection

   Momeni, Saleh; Xiao, Changnan; Liu, Bing (December 2025, The Thirty-ninth Annual Conference on Neural Information Processing Systems)

   This paper studies the problem of class-incremental learning (CIL), a core setting within continual learning where a model learns a sequence of tasks, each containing a distinct set of classes. Traditional CIL methods, which do not leverage pretrained models (PTMs), suffer from catastrophic forgetting (CF) due to the need to incrementally learn both feature representations and the classifier. The integration of PTMs into CIL has recently led to efficient approaches that treat the PTM as a fixed feature extractor combined with analytic classifiers, achieving state-ofthe-art performance. However, they still face a major limitation: the inability to continually adapt feature representations to best suit the CIL tasks, leading to suboptimal performance. To address this, we propose AnaCP (Analytic Contrastive Projection), a novel method that preserves the efficiency of analytic classifiers while enabling incremental feature adaptation without gradient-based training, thereby eliminating the CF caused by gradient updates. Our experiments show that AnaCP not only outperforms existing baselines but also achieves the accuracy level of joint training, which is regarded as the upper bound of CIL. 

   more » « less
4. Connecting Pre-trained Language Models and Downstream Tasks via Properties of Representations

   Wu, Chenwei; Lee, Holden; Ge, Rong (December 2023, NeurIPS 2023)

   Recently, researchers have found that representations learned by large-scale pretrained language models are useful in various downstream tasks. However, there is little theoretical understanding of how pre-training performance is related to downstream task performance. In this paper, we analyze how this performance transfer depends on the properties of the downstream task and the structure of the representations. We consider a log-linear model where a word can be predicted from its context through a network having softmax as its last layer. We show that even if the downstream task is highly structured and depends on a simple function of the hidden representation, there are still cases when a low pre-training loss cannot guarantee good performance on the downstream task. On the other hand, we propose and empirically validate the existence of an “anchor vector” in the representation space, and show that this assumption, together with properties of the downstream task, guarantees performance transfer. 

   more » « less
5. When BERT meets Bilbo: a learning curve analysis of pretrained language model on disease classification

   https://doi.org/10.1186/s12911-022-01829-2  

   Li, Xuedong; Yuan, Walter; Peng, Dezhong; Mei, Qiaozhu; Wang, Yue (November 2021, BMC Medical Informatics and Decision Making)

   Abstract Background Natural language processing (NLP) tasks in the health domain often deal with limited amount of labeled data due to high annotation costs and naturally rare observations. To compensate for the lack of training data, health NLP researchers often have to leverage knowledge and resources external to a task at hand. Recently, pretrained large-scale language models such as the Bidirectional Encoder Representations from Transformers (BERT) have been proven to be a powerful way of learning rich linguistic knowledge from massive unlabeled text and transferring that knowledge to downstream tasks. However, previous downstream tasks often used training data at such a large scale that is unlikely to obtain in the health domain. In this work, we aim to study whether BERT can still benefit downstream tasks when training data are relatively small in the context of health NLP. Method We conducted a learning curve analysis to study the behavior of BERT and baseline models as training data size increases. We observed the classification performance of these models on two disease diagnosis data sets, where some diseases are naturally rare and have very limited observations (fewer than 2 out of 10,000). The baselines included commonly used text classification models such as sparse and dense bag-of-words models, long short-term memory networks, and their variants that leveraged external knowledge. To obtain learning curves, we incremented the amount of training examples per disease from small to large, and measured the classification performance in macro-averaged $$F_{1}$$ F 1 score. Results On the task of classifying all diseases, the learning curves of BERT were consistently above all baselines, significantly outperforming them across the spectrum of training data sizes. But under extreme situations where only one or two training documents per disease were available, BERT was outperformed by linear classifiers with carefully engineered bag-of-words features. Conclusion As long as the amount of training documents is not extremely few, fine-tuning a pretrained BERT model is a highly effective approach to health NLP tasks like disease classification. However, in extreme cases where each class has only one or two training documents and no more will be available, simple linear models using bag-of-words features shall be considered. 

   more » « less