Search Results for author:
Found 22 papers, 13 papers with code
Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities.
Clarify: Improving Model Robustness With Natural Language Corrections
Additionally, we use Clarify to find and rectify 31 novel hard subpopulations in the ImageNet dataset, improving minority-split accuracy from 21. 1% to 28. 7%.
AutoFT: Learning an Objective for Robust Fine-Tuning
Given a task, AutoFT searches for a fine-tuning procedure that enhances out-of-distribution (OOD) generalization.
Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts
Effective machine learning models learn both robust features that directly determine the outcome of interest (e. g., an object with wheels is more likely to be a car), and shortcut features (e. g., an object on a road is more likely to be a car).
Conservative Prediction via Data-Driven Confidence Minimization
Taking inspiration from this result, we present data-driven confidence minimization (DCM), which minimizes confidence on an uncertainty dataset containing examples that the model is likely to misclassify at test time.
Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features
Transfer learning with a small amount of target data is an effective and common approach to adapting a pre-trained model to distribution shifts.
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
In this paper, we identify a property of the structure of an LLM's probability function that is useful for such detection.
Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time
Temporal shifts -- distribution shifts arising from the passage of time -- often occur gradually and have the additional structure of timestamp metadata.
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
A common approach to transfer learning under distribution shift is to fine-tune the last few layers of a pre-trained model, preserving learned features while also adapting to the new task.
On Divergence Measures for Bayesian Pseudocoresets
Finally, we propose a novel Bayesian pseudocoreset algorithm based on minimizing forward KL divergence.
Diversify and Disambiguate: Learning From Underspecified Data
Many datasets are underspecified: there exist multiple equally viable solutions to a given task.
Diversity Matters When Learning From Ensembles
We propose a simple approach for reducing this gap, i. e., making the distilled performance close to the full ensemble.
On The Distribution of Penultimate Activations of Classification Networks
This paper studies probability distributions of penultimate activations of classification networks.
Amortized Probabilistic Detection of Communities in Graphs
While graph neural networks (GNNs) have been successful in encoding graph structures, existing GNN-based methods for community detection are limited by requiring knowledge of the number of communities in advance, in addition to lacking a proper probabilistic formulation to handle uncertainty.
Neural Complexity Measures
While various complexity measures for deep neural networks exist, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven challenging.
Bootstrapping Neural Processes
While this "data-driven" way of learning stochastic processes has proven to handle various types of data, NPs still rely on an assumption that uncertainty in stochastic processes is modeled by a single latent variable, which potentially limits the flexibility.
Deep Amortized Clustering
We propose a deep amortized clustering (DAC), a neural architecture which learns to cluster datasets efficiently using a few forward passes.
Discrete InfoMax Codes for Meta-Learning
This paper analyzes how generalization works in meta-learning.
Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning
Without relevant human priors, neural networks may learn uninterpretable features.
Discrete Infomax Codes for Supervised Representation Learning
In this paper we present a model that produces Discrete InfoMax Codes (DIMCO); we learn a probabilistic encoder that yields k-way d-dimensional codes associated with input data.
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances.
Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
Our primary contribution is the {\em MT-net}, which enables the meta-learner to learn on each layer's activation space a subspace that the task-specific learner performs gradient descent on.
