Results 11 to 20 of about 1,055,420 (393)
Improved Distribution Matching for Dataset Condensation [PDF]
Computer Vision and Pattern Recognition, 2023 Dataset Condensation aims to condense a large dataset into a smaller one while maintaining its ability to train a well-performing model, thus reducing the storage cost and training effort in deep learning applications.
Ganlong Zhao +3 more
semanticscholar +1 more source
Dataset Condensation with Distribution Matching [PDF]
IEEE Workshop/Winter Conference on Applications of Computer Vision, 2021 Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset condensation that aims to
Bo Zhao, Hakan Bilen
semanticscholar +1 more source
Dataset Condensation via Efficient Synthetic-Data Parameterization [PDF]
International Conference on Machine Learning, 2022 The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning.
Jang-Hyun Kim +7 more
semanticscholar +1 more source
Higher Gauging and Non-invertible Condensation Defects [PDF]
Communications in Mathematical Physics, 2022 We discuss invertible and non-invertible topological condensation defects arising from gauging a discrete higher-form symmetry on a higher codimensional manifold in spacetime, which we define as higher gauging.
Konstantinos Roumpedakis +2 more
semanticscholar +1 more source
DC-BENCH: Dataset Condensation Benchmark [PDF]
Neural Information Processing Systems, 2022 Dataset Condensation is a newly emerging technique aiming at learning a tiny dataset that captures the rich information encoded in the original dataset.
Justin Cui +3 more
semanticscholar +1 more source
Journal of High Energy Physics, 2022 Abstract It was argued in [1] that the Volkov-Akulov (VA) model as well as similar models in supergravity and the related KKLT model in string theory, suffer from tachyonic instabilities due to goldstino condensation. The authors of [1] constructed a specific model with two unconstrained interacting chiral superfields with linearly
Renata Kallosh +3 more
openaire +3 more sources
Theory of Bose-Einstein condensation in trapped gases [PDF]
, 1998 The phenomenon of Bose-Einstein condensation of dilute gases in traps is reviewed from a theoretical perspective. Mean-field theory provides a framework to understand the main features of the condensation and the role of interactions between particles ...
F. Dalfovo +4 more
semanticscholar +1 more source
To condense or not to condense? That is the question
Physics Letters B, 1992 Abstract We investigate the dependence of the pion mass in the nuclear medium with density and the condition for s-wave pion condensation. We base our approach on multiple scattering and the consistent use of the chiral off-mass-shell properties of the πN amplitude.
J. Delorme +2 more
openaire +2 more sources
Bose-Einstein condensation and condensation of $q$-particles in equilibrium and non equilibrium thermodynamics: a new approach [PDF]
, 2015 In the setting of the principle of local equilibrium which asserts that the temperature is a function of the energy levels of the system, we exhibit plenty of steady states describing the condensation of free Bosons which are not in thermal equilibrium ...
Accardi, Luigi, Fidaleo, Francesco
core +2 more sources
A third family of super dense stars in the presence of antikaon condensates [PDF]
, 2001 The formation of $K^-$ and $\bar K^0$ condensation in $\beta$-equilibrated hyperonic matter is investigated within a relativistic mean field model. In this model, baryon-baryon and (anti)kaon-baryon interactions are mediated by the exchange of mesons. It
Bandyopadhyay, Debades, Banik, Sarmistha
core +3 more sources