FlashOptim's memory compression of optimizer states can be combined with low-rank momentum approximation to achieve sub-linear memory scaling in transformer training.
Adversarial Debate Score
50% survival rate under critique
Model Critiques
Supporting Research Papers
- Cheap Thrills: Effective Amortized Optimization Using Inexpensive Labels
To scale the solution of optimization and simulation problems, prior work has explored machine-learning surrogates that inexpensively map problem parameters to corresponding solutions. Commonly used a...
- FlashOptim: Optimizers for Memory Efficient Training
Standard mixed-precision training of neural networks requires many bytes of accelerator memory for each model parameter. These bytes reflect not just the parameter itself, but also its gradient and on...
- Universal Persistent Brownian Motions in Confluent Tissues
Biological tissues are active materials whose non-equilibrium dynamics emerge from distinct cellular force-generating mechanisms. Using a two-dimensional active foam model, we compare the effects of t...
- Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks
The advancement of large language models (LLMs) has accelerated the development of autonomous financial trading systems. While mainstream approaches deploy multi-agent systems mimicking analyst and ma...
Formal Verification
Z3 checks whether the hypothesis is internally consistent, not whether it is empirically true.