Search Results for author:
Found 21 papers, 8 papers with code
Position Paper: Generalized grammar rules and structure-based generalization beyond classical equivariance for lexical tasks and transduction
Compositional generalization is one of the main properties which differentiates lexical learning in humans from state-of-art neural networks.
Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
Large language models (LLMs) specializing in natural language generation (NLG) have recently started exhibiting promising capabilities across a variety of domains.
Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control
We focus on a typical scenario where such requirements, separately encoding $\textit{value}$ and $\textit{cost}$, compete with each other.
Conformal Prediction Intervals with Temporal Dependence
We focus on the task of constructing valid prediction intervals (PIs) in time series regression with a cross-section.
Conformal Prediction with Temporal Quantile Adjustments
TQA adjusts the quantile to query in CP at each time $t$, accounting for both cross-sectional and longitudinal coverage in a theoretically-grounded manner.
Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks
Most existing calibration methods either lack theoretical guarantees for producing calibrated outputs, reduce classification accuracy in the process, or only calibrate the predicted class.
Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?
We find that the fraction of separable dichotomies is determined by the dimension of the space that is fixed by the group action.
Locally Valid and Discriminative Prediction Intervals for Deep Learning Models
Moreover, when combined with deep learning (DL) methods, it should be scalable and affect the DL model performance minimally.
DeepSZ: Identification of Sunyaev-Zel'dovich Galaxy Clusters using Deep Learning
We present a comparison between two methods of cluster identification: the standard Matched Filter (MF) method in SZ cluster finding and a method using Convolutional Neural Networks (CNN).
Rotation-Invariant Autoencoders for Signals on Spheres
These newly proposed convolutional layers naturally extend the notion of convolution to functions on the unit sphere $S^2$ and the group of rotations $SO(3)$ and these layers are equivariant to 3D rotations.
The Expected Jacobian Outerproduct: Theory and Empirics
The expected gradient outerproduct (EGOP) of an unknown regression function is an operator that arises in the theory of multi-index regression, and is known to recover those directions that are most relevant to predicting the output.
Asymmetric Multiresolution Matrix Factorization
Multiresolution Matrix Factorization (MMF) was recently introduced as an alternative to the dominant low-rank paradigm in order to capture structure in matrices at multiple different scales.
Deep Learning for Automated Classification and Characterization of Amorphous Materials
The characterization of amorphous materials is especially challenging because their lack of long-range order makes it difficult to define structural metrics.
Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
Recent work by Cohen et al. has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis.
DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
In this work, we demonstrate reconstruction of the CMB lensing potential with deep convolutional neural networks (CNN) - ie, a ResUNet.
Discriminative Learning of Similarity and Group Equivariant Representations
We also present extensions of this formulation to metric learning for kNN regression, asymmetric similarity learning and discriminative learning of Hamming distance.
Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
Recent work by Cohen \emph{et al.} has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis.
On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
In this paper we give a rigorous, theoretical treatment of convolution and equivariance in neural networks with respect to not just translations, but the action of any compact group.
Covariant Compositional Networks For Learning Graphs
Most existing neural networks for learning graphs address permutation invariance by conceiving of the network as a message passing scheme, where each node sums the feature vectors coming from its neighbors.
The Utility of Clustering in Prediction Tasks
Previous work has hinted at the improvement in prediction accuracy attributed to clustering algorithms if used to pre-process the data.
Discriminative Metric Learning by Neighborhood Gerrymandering
We formulate the problem of metric learning for k nearest neighbor classification as a large margin structured prediction problem, with a latent variable representing the choice of neighbors and the task loss directly corresponding to classification error.
