Search Results for author:
Found 19 papers, 5 papers with code
TADPOLE: Task ADapted Pre-Training via AnOmaLy DEtection
In this paper, we address the problem for the case when the downstream corpus is too small for additional pre-training.
Representation Projection Invariance Mitigates Representation Collapse
In this paper, we propose Representation Projection Invariance (REPINA), a novel regularization method to maintain the information content of representation and reduce representation collapse during fine-tuning by discouraging undesirable changes in the representations.
Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection
Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive.
Domain Adaptation via Anaomaly Detection
The need for such a method is clear as it is infeasible to collect a large pre-training corpus for every possible domain.
TabTransformer: Tabular Data Modeling Using Contextual Embeddings
We propose TabTransformer, a novel deep tabular data modeling architecture for supervised and semi-supervised learning.
PruneNet: Channel Pruning via Global Importance
The methods that start with a pretrained network either prune channels uniformly across the layers or prune channels based on the basic statistics of the network parameters.
schuBERT: Optimizing Elements of BERT
In this work we revisit the architecture choices of BERT in efforts to obtain a lighter model.
Differentiable Architecture Compression
In many learning situations, resources at inference time are significantly more constrained than resources at training time.
Robust conditional GANs under missing or uncertain labels
Matching the performance of conditional Generative Adversarial Networks with little supervision is an important task, especially in venturing into new domains.
DARC: Differentiable ARchitecture Compression
In many learning situations, resources at inference time are significantly more constrained than resources at training time.
Number of Connected Components in a Graph: Estimation via Counting Patterns
This representation is crucial in introducing a novel estimator for the number of connected components for general graphs, under the knowledge of the spectral gap of the original graph.
Robustness of Conditional GANs to Noisy Labels
When the distribution of the noise is known, we introduce a novel architecture which we call Robust Conditional GAN (RCGAN).
Learning From Noisy Singly-labeled Data
We propose a new algorithm for jointly modeling labels and worker quality from noisy crowd-sourced data.
PacGAN: The power of two samples in generative adversarial networks
Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples.
Matrix Norm Estimation from a Few Entries
This paper focuses on the technical challenges in accurately estimating the Schatten norms from a sampling of a matrix.
Spectrum Estimation from a Few Entries
We propose first estimating the Schatten $k$-norms of a matrix, and then applying Chebyshev approximation to the spectral sum function or applying moment matching in Wasserstein distance to recover the singular values.
Computational and Statistical Tradeoffs in Learning to Rank
For massive and heterogeneous modern datasets, it is of fundamental interest to provide guarantees on the accuracy of estimation when computational resources are limited.
Achieving Budget-optimality with Adaptive Schemes in Crowdsourcing
Under this generalized Dawid-Skene model, we characterize the fundamental trade-off between budget and accuracy.
Data-driven Rank Breaking for Efficient Rank Aggregation
Rank aggregation systems collect ordinal preferences from individuals to produce a global ranking that represents the social preference.
