A seguirPróximo guia
Descida Gradiente
Fundamentos
GUIA de fundamentos
Double descent is an observed pattern in which test error can rise near the point where a model first interpolates the training data, then fall again as capacity increases.
Ouça este guiaNarrado por IA · ~2 min
It shows that added model complexity does not always worsen test performance, though the curve depends on the model, data, and training setup.
Classical statistics teaches a U-shaped curve: as model complexity rises, test error falls, bottoms out, then rises as the model overfits. Double descent, popularized by Belkin, Hsu, Ma, and Mandal in 2019 and studied at scale by OpenAI, shows the curve has a second descent. Test error peaks near the interpolation threshold — the point where the model has just enough parameters to fit every training point exactly (zero training error). Push past that into the overparameterized regime and test error can fall again, sometimes below the classical sweet spot. OpenAI reported the phenomenon in convolutional neural networks, ResNets, and transformers; the shape and location varied by experiment. Related double-descent behavior can also appear as training duration or dataset size changes, so it is not a guarantee that every larger model will improve.
Studying how test error changes as model capacity passes the point of fitting the training set
Measuring whether training duration produces a second rise and fall in test error for a particular setup
Comparing models and datasets where increasing training-set size has different effects near interpolation
Using validation curves to understand a model’s behavior rather than assuming that a larger model always generalizes worse
Research continues to connect double descent with model class, effective complexity, implicit regularization, and optimization. The phenomenon can guide experiments on model size and training duration, but it does not prescribe that practitioners should always train larger models or longer. Validation under the target data and deployment conditions remains necessary.
Boletim informativo gratuito
Três histórias verificadas de IA a cada manhã de dia útil, escritas em linguagem simples. Gratuito para sempre, sem anúncios.
Um e-mail a cada dia útil. Cancele a inscrição com um clique. Nunca vendemos ou compartilhamos seu endereço.
Teste você mesmo
Feedback instantâneo sobre cada resposta e um certificado compartilhável com um ID verificável assim que você concluir um curso.
Apoie a educação gratuita em IA. O AI Understanding é uma organização sem fins lucrativos 501(c)(3) — sem anúncios, sem paywall, nunca. Faça uma doação
Double descent is an observed pattern in which test error can rise near the point where a model first interpolates the training data, then fall again as capacity increases. It shows that added model complexity does not always worsen test performance, though the curve depends on the model, data, and training setup.
In reported double-descent experiments, test error peaks near the interpolation threshold, where training error first reaches zero; the location and shape depend on the setup.
No regime superparametrizado, o erro de teste desce uma segunda vez, que é a característica definidora que dá nome à descida dupla.
A specific analysis of single-hidden-layer linear networks proves a minimum-norm result under its gradient-flow and initialization assumptions; this is not a general result for all neural networks.
A descida dupla pode ocorrer ao longo do eixo tempo de treinamento: o erro do teste pode piorar e depois melhorar à medida que o treinamento continua por mais épocas.
Isso contradiz a curva em forma de U do livro didático, que diz que mais complexidade além de um ponto sempre aumenta o erro do teste por meio de overfitting.
Continue aprendendo
Mais guias escolhidos para este tópico
A seguirPróximo guia
Descida Gradiente
Fundamentos