research
∙
08/25/2023
Fine-tuning can cripple your foundation model; preserving features may be the solution
Pre-trained foundation models, owing primarily to their enormous capacit...
share
research
∙
07/23/2023
In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning
The performance of Large Language Models (LLMs) on downstream tasks ofte...
research
∙
07/20/2023
LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
Large language models (LLMs) have exhibited impressive capabilities in c...
research
∙
06/26/2023
BatchGFN: Generative Flow Networks for Batch Active Learning
We introduce BatchGFN – a novel approach for pool-based active learning ...
research
∙
06/02/2023
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
In this paper, we introduce a novel method for enhancing the effectivene...
research
∙
05/27/2023
The Curse of Recursion: Training on Generated Data Makes Models Forget
Stable Diffusion revolutionised image creation from descriptive text. GP...
research
∙
04/17/2023
Prediction-Oriented Bayesian Active Learning
Information-theoretic approaches to active learning have traditionally f...
research
∙
04/07/2023
Revisiting Automated Prompting: Are We Actually Doing Better?
Current literature demonstrates that Large Language Models (LLMs) are gr...
research
∙
02/21/2023
Differentiable Multi-Target Causal Bayesian Experimental Design
We introduce a gradient-based approach for the problem of Bayesian optim...
research
∙
02/19/2023
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
We introduce a method to measure uncertainty in large language models. F...
research
∙
12/28/2022
On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
KL-regularized reinforcement learning from expert demonstrations has pro...
research
∙
12/15/2022
CLAM: Selective Clarification for Ambiguous Questions with Large Language Models
State-of-the-art language models are often accurate on many question-ans...
research
∙
11/23/2022
Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks
Bayesian deep learning seeks to equip deep neural networks with the abil...
research
∙
11/13/2022
Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels
Automated planetary transit detection has become vital to prioritize can...
research
∙
09/27/2022
Exploring Low Rank Training of Deep Neural Networks
Training deep neural networks in low rank, i.e. with factorised layers, ...
research
∙
08/19/2022
Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation
The Solar Dynamics Observatory (SDO), a NASA multi-spectral decade-long ...
research
∙
08/01/2022
Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities
The mutual information between predictions and model parameters – also r...
research
∙
06/14/2022
Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
Training on web-scale data can take months. But most computation and tim...
research
∙
06/05/2022
Learning Dynamics and Generalization in Reinforcement Learning
Solving a reinforcement learning (RL) problem poses two competing challe...
research
∙
05/27/2022
Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval
The ability to accurately model the fitness landscape of protein sequenc...
research
∙
05/18/2022
Marginal and Joint Cross-Entropies Predictives for Online Bayesian Inference, Active Learning, and Active Sampling
Principled Bayesian deep learning (BDL) does not live up to its potentia...
research
∙
04/21/2022
Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions
Estimating the effects of continuous-valued interventions from observati...
research
∙
03/03/2022
Interventions, Where and How? Experimental Design for Causal Models at Scale
Causal discovery from observational and interventional data is challengi...
research
∙
02/16/2022
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients
Pruning neural networks at initialization would enable us to find sparse...
research
∙
02/14/2022
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
We propose Active Surrogate Estimators (ASEs), a new method for label-ef...
research
∙
02/03/2022
A Note on "Assessing Generalization of SGD via Disagreement"
Jiang et al. (2021) give empirical evidence that the average test error ...
research
∙
12/24/2021
DARTS without a Validation Set: Optimizing the Marginal Likelihood
The success of neural architecture search (NAS) has historically been li...
research
∙
12/01/2021
Decomposing Representations for Deterministic Uncertainty Estimation
Uncertainty estimation is a key component in any deployed machine learni...
research
∙
11/29/2021
DeDUCE: Generating Counterfactual Explanations Efficiently
When an image classifier outputs a wrong class label, it can be helpful ...
research
∙
11/15/2021
Contrastive Representation Learning with Trainable Augmentation Channel
In contrastive representation learning, data representation is trained s...
research
∙
11/05/2021
Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation
High resolution remote sensing imagery is used in broad range of tasks, ...
research
∙
11/03/2021
Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data
Estimating personalized treatment effects from high-dimensional observat...
research
∙
10/29/2021
Deep Deterministic Uncertainty for Semantic Segmentation
We extend Deep Deterministic Uncertainty (DDU), a method for uncertainty...
research
∙
10/28/2021
Using Non-Linear Causal Models to Study Aerosol-Cloud Interactions in the Southeast Pacific
Aerosol-cloud interactions include a myriad of effects that all begin wh...
research
∙
10/22/2021
GeneDisco: A Benchmark for Experimental Design in Drug Discovery
In vitro cellular experimentation with genetic interventions, using for ...
research
∙
07/29/2021
Quantifying Uncertainty for Machine Learning Based Diagnostic
Virtual Diagnostic (VD) is a deep learning tool that can be used to pred...
research
∙
07/15/2021
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
There has been significant research done on developing methods for impro...
research
∙
07/06/2021
Prioritized training on points that are learnable, worth learning, and not yet learned
We introduce Goldilocks Selection, a technique for faster model training...
research
∙
06/30/2021
Improving black-box optimization in VAE latent space using decoder uncertainty
Optimization in the latent space of variational autoencoders is a promis...
research
∙
06/22/2021
A Practical Unified Notation for Information-Theoretic Quantities in ML
Information theory is of importance to machine learning, but the notatio...
research
∙
06/22/2021
A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions
In active learning, new labels are commonly acquired in batches. However...
research
∙
06/22/2021
Active Learning under Pool Set Distribution Shift and Noisy Data
Active Learning is essential for more label-efficient deep learning. Bay...
research
∙
06/14/2021
KL Guided Domain Adaptation
Domain adaptation is an important problem and often needed for real-worl...
research
∙
06/07/2021
Uncertainty Baselines: Benchmarks for Uncertainty Robustness in Deep Learning
High-quality estimates of uncertainty and robustness are crucial for num...
research
∙
06/04/2021
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
We challenge a common assumption underlying most supervised deep learnin...
research
∙
06/04/2021
Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
ResNets constrained to be bi-Lipschitz, that is, approximately distance ...
research
∙
04/20/2021
Outcome-Driven Reinforcement Learning via Variational Inference
While reinforcement learning algorithms provide automated acquisition of...
research
∙
04/10/2021
Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization
As climate change increases the intensity of natural disasters, society ...
research
∙
03/16/2021
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Counterfactual explanations (CEs) are a practical tool for demonstrating...
research
∙
03/10/2021