Inductive Learning
Few-Shot Task Learning through Inverse Generative Modeling
Learning the intents of an agent, defined by its goals or motion style, is often extremely challenging from just a few examples.
Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT Thomas Y erxa
"contrastive-equivariant" versions that encourage preservation of input transformations without supervised access to the transformation parameters.
Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping Yingbin Bai 1 Zhongyi Han 2 Erkun Y ang 3 Jun Y u 4
Most existing approaches for dealing with noisy labels broadly fall into two categories: noise-modeling-based methods and memorization-effects-based methods.
Improving Subgroup Robustness via Data Selection
Machine learning models can often fail on subgroups that are underrepresented during training.
From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader
Discriminative methods were used to execute such tasks and achieved state-of-the-art performance.
Neural Priming for Sample-Efficient Adaptation Matthew Wallingford Vivek Ramanujan Alex Fang Aditya Kusupati
Presented with class names or unlabeled test samples, Neural Priming enables the model to recall and conditions its parameters on relevant data seen throughout pretraining, thereby priming it for the test distribution. Neural Priming can be performed at inference, even for pretraining datasets as large as LAION-2B. Performing lightweight updates on the recalled data significantly improves accuracy across a variety of distribution shift and transfer learning benchmarks.
The Gain of Ordering in Online Learning
V ov95, CBL06] and online convex optimization [Haz16, Ora19] have been developed. Until the labels of all examples of X have been predicted: The learning algorithm picks a point x X and makes a prediction z R about its label.
