Search Results for author:
Found 28 papers, 13 papers with code
Foundation Posteriors for Approximate Probabilistic Inference
Given a probabilistic program, we are interested in the task of posterior inference: estimating a latent variable given a set of observed variables.
Know Thy Student: Interactive Learning with Gaussian Processes
The teacher must interact and diagnose the student, before teaching.
Tutela: An Open-Source Tool for Assessing User-Privacy on Ethereum and Tornado Cash
Mixers, such as Tornado Cash, were developed to preserve privacy through "mixing" transactions with those of others in an anonymity pool, making it harder to link deposits and withdrawals from the pool.
Tradeoffs Between Contrastive and Supervised Learning: An Empirical Study
Contrastive learning has made considerable progress in computer vision, outperforming supervised pretraining on a range of downstream datasets.
Temperature as Uncertainty in Contrastive Learning
In this paper, we propose a simple way to generate uncertainty scores for many contrastive methods by re-purposing temperature, a mysterious hyperparameter used for scaling.
Modeling Item Response Theory with Stochastic Variational Inference
Item Response Theory (IRT) is a ubiquitous model for understanding human behaviors and attitudes based on their responses to questions.
ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
High-quality computer science education is limited by the difficulty of providing instructor feedback to students at scale.
Improving Compositionality of Neural Networks by Decoding Representations to Inputs
In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together.
HarperValleyBank: A Domain-Specific Spoken Dialog Corpus
We introduce HarperValleyBank, a free, public domain spoken dialog corpus.
Viewmaker Networks: Learning Views for Unsupervised Representation Learning
However, designing these views requires considerable trial and error by human experts, hindering widespread adoption of unsupervised representation learning methods across domains and modalities.
Conditional Negative Sampling for Contrastive Learning of Visual Representations
To do this, we introduce a family of mutual information estimators that sample negatives conditionally -- in a "ring" around each positive.
A Simple Framework for Uncertainty in Contrastive Learning
Contrastive approaches to representation learning have recently shown great promise.
On Mutual Information in Contrastive Learning for Visual Representations
Reformulating previous learning objectives in terms of mutual information also simplifies and stabilizes them.
Variational Item Response Theory: Fast, Accurate, and Expressive
Item Response Theory (IRT) is a ubiquitous model for understanding humans based on their responses to questions, used in fields as diverse as education, medicine and psychology.
Multimodal Generative Models for Compositional Representation Learning
As part of our derivation we find that many previous multimodal variational autoencoders used objectives that do not correctly bound the joint marginal likelihood across modalities.
Gradient Boosting Machine: A Survey
In this survey, we discuss several different types of gradient boosting algorithms and illustrate their mathematical frameworks in detail: 1. introduction of gradient boosting leads to 2. objective function optimization, 3. loss function estimations, and 4. model constructions.
Optimizing for Interpretability in Deep Neural Networks with Tree Regularization
Moreover, for situations in which a single, global tree is a poor estimator, we introduce a regional tree regularizer that encourages the deep model to resemble a compact, axis-aligned decision tree in predefined, human-interpretable contexts.
Regional Tree Regularization for Interpretability in Black Box Models
The lack of interpretability remains a barrier to the adoption of deep neural networks.
Generative Grading: Near Human-level Accuracy for Automated Feedback on Richly Structured Problems
In this paper, we present generative grading: a novel computational approach for providing feedback at scale that is capable of accurately grading student work and providing nuanced, interpretable feedback.
Pragmatic inference and visual abstraction enable contextual flexibility during visual communication
On each trial, both participants were shown the same four objects, but in different locations.
Meta-Amortized Variational Inference and Learning
Despite the recent success in probabilistic modeling and their applications, generative models trained using traditional inference techniques struggle to adapt to new distributions, even when the target distribution may be closely related to the ones seen during training.
Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference
Stochastic optimization techniques are standard in variational inference algorithms.
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
Rubric sampling requires minimal teacher effort, can associate feedback with specific parts of a student's solution and can articulate a student's misconceptions in the language of the instructor.
Multimodal Generative Models for Scalable Weakly-Supervised Learning
Multiple modalities often co-occur when describing natural phenomena.
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
The lack of interpretability remains a key barrier to the adoption of deep models in many applications.
Spreadsheet Probabilistic Programming
We demonstrate this by developing a native Excel implementation of both a particle Markov Chain Monte Carlo variant and black-box variational inference for spreadsheet probabilistic programming.
Position and Vector Detection of Blind Spot motion with the Horn-Schunck Optical Flow
The proposed method uses live image footage which, based on calculations of pixel motion, decides whether or not an object is in the blind-spot.
Financial Market Prediction
Given financial data from popular sites like Yahoo and the London Exchange, the presented paper attempts to model and predict stocks that can be considered "good investments".
