Lift: Language-interfaced fine-tuning for non-language machine learning tasks
Fine-tuning pretrained language models (LMs) without making any architectural changes
has become a norm for learning various language downstream tasks. However, for non …
has become a norm for learning various language downstream tasks. However, for non …
The emergence of reproducibility and consistency in diffusion models
In this work, we investigate an intriguing and prevalent phenomenon of diffusion models
which we term as" consistent model reproducibility'': given the same starting noise input and …
which we term as" consistent model reproducibility'': given the same starting noise input and …
Is Ockham's razor losing its edge? New perspectives on the principle of model parsimony
The preference for simple explanations, known as the parsimony principle, has long guided
the development of scientific theories, hypotheses, and models. Yet recent years have seen …
the development of scientific theories, hypotheses, and models. Yet recent years have seen …
Simplifying neural network training under class imbalance
Real-world datasets are often highly class-imbalanced, which can adversely impact the
performance of deep learning models. The majority of research on training neural networks …
performance of deep learning models. The majority of research on training neural networks …
Latent space translation via semantic alignment
While different neural models often exhibit latent spaces that are alike when exposed to
semantically related data, this intrinsic similarity is not always immediately discernible …
semantically related data, this intrinsic similarity is not always immediately discernible …
Rashomon capacity: A metric for predictive multiplicity in classification
Predictive multiplicity occurs when classification models with statistically indistinguishable
performances assign conflicting predictions to individual samples. When used for decision …
performances assign conflicting predictions to individual samples. When used for decision …
Similarity of neural network models: A survey of functional and representational measures
M Klabunde, T Schumacher, M Strohmaier… - ar** deep learning models, we usually decide what task we want to solve then
search for a model that generalizes well on the task. An intriguing question would be: what if …
search for a model that generalizes well on the task. An intriguing question would be: what if …