Ryadh Khsib's repositories
aws-serverlessrepo-python
A Python library with convenience helpers for working with the AWS Serverless Application Repository.
BayesianSumProductNetworks
Implementation of Bayesian Sum-Product Networks
cgpm
Library of composable generative population models which serve as the modeling and inference backend of BayesDB.
Classification-AD
Repository for the paper "Rethinking Assumptions in Anomaly Detection"
crosscat
A domain-general, Bayesian method for analyzing high-dimensional data tables
DAMO-ConvAI
DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.
DeepStructuredMixtures
Code for Deep Structured Mixtures of Gaussian Processes (DSMGPs)
DGEMO
[NeurIPS 2020] Diversity-Guided Efficient Multi-Objective Optimization With Batch Evaluations
dropout_icml2019
Code to reproduce the experiments reported in "Dropout as a Structured Shrinkage Prior" [Nalisnick et al., ICML 2019]
Financial-Models-Numerical-Methods
Collection of notebooks about quantitative finance, with interactive python code.
eop
Code for the paper "Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters", ICML 2022
forecastNet
Code for the paper entitled "ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series Forecasting"
go-explore
Code for Go-Explore: a New Approach for Hard-Exploration Problems
google-research
Google Research
LipschitzRNN
Lipschitz Recurrent Neural Networks
morbo
Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces
RccGAN
Regularized Compound Conditional GAN for Large-Scale Tabular Data Synthesis
RVAE_MixedTypes
Repository for code release of paper "Robust Variational Autoencoders for Outlier Detection and Repair of Mixed-Type Data" (AISTATS 2020)
Sampling-free-Epistemic-Uncertainty
Code for the ICCV 2019 paper "Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation"
TimeMachine
TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting
trcrpm
Temporally-reweighted Chinese restaurant process mixture models for multivariate time series
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)