DeepONet learns nonlinear operators for differential equations via branch and trunk sub-networks, achieving high-order error convergence on small datasets.
Universal function approximation by deep neural nets with bounded width and relu activations
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Establishes convergence guarantees for overparameterized 2-layer ReLU networks in flow matching, generalization bounds for the velocity-field objective, and Wasserstein guarantees for generated samples, using multi-task representation learning bounds.
SPIN lets weak LLMs become strong by self-generating training data from previous model versions and training to prefer human-annotated responses over its own outputs, outperforming DPO even with extra GPT-4 data on benchmarks.
DNNs approximate sequences of functions constructed via finite compositions of locally Lipschitz continuous functions, maxima, and products with polynomial parameter growth in d and 1/ε.
Invariance-inducing regularization using worst-case transformations reduces relative error by 20% on CIFAR10 transformed examples, improves standard accuracy on SVHN, outperforms equivariant networks, and proves no accuracy-robustness trade-off in the infinite data limit.
citing papers explorer
-
DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
DeepONet learns nonlinear operators for differential equations via branch and trunk sub-networks, achieving high-order error convergence on small datasets.
-
A Theory on Flow Matching with Neural Networks
Establishes convergence guarantees for overparameterized 2-layer ReLU networks in flow matching, generalization bounds for the velocity-field objective, and Wasserstein guarantees for generated samples, using multi-task representation learning bounds.
-
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
SPIN lets weak LLMs become strong by self-generating training data from previous model versions and training to prefer human-annotated responses over its own outputs, outperforming DPO even with extra GPT-4 data on benchmarks.
-
Deep neural network approximation theory for high-dimensional functions
DNNs approximate sequences of functions constructed via finite compositions of locally Lipschitz continuous functions, maxima, and products with polynomial parameter growth in d and 1/ε.
-
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
Invariance-inducing regularization using worst-case transformations reduces relative error by 20% on CIFAR10 transformed examples, improves standard accuracy on SVHN, outperforms equivariant networks, and proves no accuracy-robustness trade-off in the infinite data limit.