Posts by Tags

AlphaTensor

Some thought on AlphaTensor

4 minute read

Published:

Recently, there is a heated attention on newly released paper AlphaTensor from DeepMind. The claim in the Abstract seems to imply that there is a great advancement for a 50 year old problem that Strassen’s algorithm was trying to address. This is really an intriguing claim, thus I spared myself some time trying to fully understand to what extent these claims are true, and how the algorithm they use looks like for such achievements.

Artificial Intelligence

AI-Aided Problem Solving

2 minute read

Published:

AI techniques/algorithms keep advancing these days, along with that is an increasing interest on the question how these techniques and algorithms shall be harnessed for solving real-world problems. In this blog, I provide some of my thoughts on problem-solving and artificial intelligence.

Problem Formulation

AI-Aided Problem Solving

2 minute read

Published:

AI techniques/algorithms keep advancing these days, along with that is an increasing interest on the question how these techniques and algorithms shall be harnessed for solving real-world problems. In this blog, I provide some of my thoughts on problem-solving and artificial intelligence.

Problem Solving

AI-Aided Problem Solving

2 minute read

Published:

AI techniques/algorithms keep advancing these days, along with that is an increasing interest on the question how these techniques and algorithms shall be harnessed for solving real-world problems. In this blog, I provide some of my thoughts on problem-solving and artificial intelligence.

artificial intelligence

The game of Hex

2 minute read

Published:

In this blog, I give an introduction to the game’s origin and key properities of the game.

board game

The game of Hex

2 minute read

Published:

In this blog, I give an introduction to the game’s origin and key properities of the game.

compiler

Deep Learning Frameworks and Compilers

3 minute read

Published:

In previous blogs, we have covered the topic of scheduling tensor programs. This task might be viewed as one step in machine learning compilers, which I will provide an introduction in this blog.

compiler optimization

Reinforcement Learning for Scheduling Tensor Programs

3 minute read

Published:

The idea of reinforcement learning has been applied for scheduling tensor programs, but so far, the RL algorithms being used are largely different from those being developed in the RL community. In this blog, I briefly summarize the existing methods, and dicuss potential and interesting working directions.

Scheduling tensor programs

2 minute read

Published:

Tensor programs are ubiquitous, ranging from general matrix muliplication to deep neural networks. However, due to extensive float number computation, execution them can incur high latency. Indeed, it is well-known that the rejuvenation of neural networks is very much due to the use of GPUs for these computation — thus accelerating tensor programs is of great importance.

game of hex

The game of Hex

2 minute read

Published:

In this blog, I give an introduction to the game’s origin and key properities of the game.

machine learning

Scheduling tensor programs

2 minute read

Published:

Tensor programs are ubiquitous, ranging from general matrix muliplication to deep neural networks. However, due to extensive float number computation, execution them can incur high latency. Indeed, it is well-known that the rejuvenation of neural networks is very much due to the use of GPUs for these computation — thus accelerating tensor programs is of great importance.

matrix multiplication

Some thought on AlphaTensor

4 minute read

Published:

Recently, there is a heated attention on newly released paper AlphaTensor from DeepMind. The claim in the Abstract seems to imply that there is a great advancement for a 50 year old problem that Strassen’s algorithm was trying to address. This is really an intriguing claim, thus I spared myself some time trying to fully understand to what extent these claims are true, and how the algorithm they use looks like for such achievements.

multi-agent learning

Multi-agent Reinforcement Learning

less than 1 minute read

Published:

In this blog I provide an introduction to the game of Pommerman, a game designed for studying multi-agent learning.

pommerman

Multi-agent Reinforcement Learning

less than 1 minute read

Published:

In this blog I provide an introduction to the game of Pommerman, a game designed for studying multi-agent learning.

reinforcement learning

Reinforcement Learning for Scheduling Tensor Programs

3 minute read

Published:

The idea of reinforcement learning has been applied for scheduling tensor programs, but so far, the RL algorithms being used are largely different from those being developed in the RL community. In this blog, I briefly summarize the existing methods, and dicuss potential and interesting working directions.

tensor program scheduling algorithms

Reinforcement Learning for Scheduling Tensor Programs

3 minute read

Published:

The idea of reinforcement learning has been applied for scheduling tensor programs, but so far, the RL algorithms being used are largely different from those being developed in the RL community. In this blog, I briefly summarize the existing methods, and dicuss potential and interesting working directions.

tensor programs

Deep Learning Frameworks and Compilers

3 minute read

Published:

In previous blogs, we have covered the topic of scheduling tensor programs. This task might be viewed as one step in machine learning compilers, which I will provide an introduction in this blog.

tensor programs and neural nets

Scheduling tensor programs

2 minute read

Published:

Tensor programs are ubiquitous, ranging from general matrix muliplication to deep neural networks. However, due to extensive float number computation, execution them can incur high latency. Indeed, it is well-known that the rejuvenation of neural networks is very much due to the use of GPUs for these computation — thus accelerating tensor programs is of great importance.