Pinned Repositories
CAGrad
FedML
A Research-oriented Federated Learning Library. Supporting distributed computing, mobile/IoT on-device training, and standalone simulation. Best Paper Award at NeurIPS 2020 Federated Learning workshop. Join our Slack Community:(https://join.slack.com/t/fedml/shared_invite/zt-havwx1ee-a1xfOUrATNfc9DFqU~r34w)
heshandevaka.github.io
minimalRL
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
ML-From-Scratch
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
MLSys2022-FLworkshop
MoCo
This repository contains the codebase used to generate the main results of "Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach, which has been accepted to ICLR 2023."
MoCo-plus
Code for implementing MoCo+ (ICASSP 2024)
Trade-Off-MOL
Experiments on trade-off among optimization, generalization and conflict aversion in multi-objective learning (MOL), and introducing MoDo.
XRIGHT
The official PyTorch implementation of ALRIGHT and MAXRIGHT algorithms for efficient trade-off in LLM post-training
heshandevaka's Repositories
heshandevaka/Trade-Off-MOL
Experiments on trade-off among optimization, generalization and conflict aversion in multi-objective learning (MOL), and introducing MoDo.
heshandevaka/XRIGHT
The official PyTorch implementation of ALRIGHT and MAXRIGHT algorithms for efficient trade-off in LLM post-training
heshandevaka/MoCo
This repository contains the codebase used to generate the main results of "Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach, which has been accepted to ICLR 2023."
heshandevaka/MoCo-plus
Code for implementing MoCo+ (ICASSP 2024)
heshandevaka/CAGrad
heshandevaka/FedML
A Research-oriented Federated Learning Library. Supporting distributed computing, mobile/IoT on-device training, and standalone simulation. Best Paper Award at NeurIPS 2020 Federated Learning workshop. Join our Slack Community:(https://join.slack.com/t/fedml/shared_invite/zt-havwx1ee-a1xfOUrATNfc9DFqU~r34w)
heshandevaka/heshandevaka.github.io
heshandevaka/minimalRL
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
heshandevaka/ML-From-Scratch
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
heshandevaka/MLSys2022-FLworkshop
heshandevaka/pareto-hypernetworks
Official implementation of Learning The Pareto Front With HyperNetworks [ICLR 2021]
heshandevaka/PCGrad
Code for "Gradient Surgery for Multi-Task Learning"
heshandevaka/RL-Adventure
Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
heshandevaka/RL-Adventure-2
PyTorch0.4 implementation of: actor critic / proximal policy optimization / acer / ddpg / twin dueling ddpg / soft actor critic / generative adversarial imitation learning / hindsight experience replay
heshandevaka/template