hyperparameter optimization
PulseAugur coverage of hyperparameter optimization — every cluster mentioning hyperparameter optimization across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New DynaBO framework allows continuous user control in Bayesian optimization
Researchers have introduced DynaBO, a novel Bayesian optimization framework designed to allow continuous user input during hyperparameter optimization. Unlike traditional methods that rely solely on initial expert knowl…
-
Snowflake simplifies ALS recommendation engine training with new HPO API
Snowflake has introduced a new API for its Hyperparameter Optimization (HPO) service, designed to simplify the distribution of training for Alternating Least Squares (ALS) recommendation engines. This feature addresses …
-
New research sharpens analysis and convergence of bilevel optimization methods
Researchers have developed new analytical frameworks and algorithms to improve the efficiency and convergence of bilevel optimization methods, which are crucial for applications like hyperparameter tuning and meta-learn…
-
LLMs can simulate high-level human behavior in operations management, but distributional accuracy varies
A new paper explores the use of large language models (LLMs) as simulators for human behavior in operations management. Researchers found that while LLMs can often replicate the high-level outcomes of behavioral-operati…
-
Bilevel optimization framework detailed for Neural Architecture Search
This paper provides a structured overview of Neural Architecture Search (NAS) by framing it as a bilevel optimization problem. It categorizes existing NAS methods into sampling-based and bilevel theory-based approaches.…
-
ASAP framework enhances ML hyperparameter optimization via agent-system co-design
Researchers have developed ASAP, a novel agent-system co-design framework for hyperparameter optimization (HPO) in machine learning experiments. ASAP addresses limitations of existing HPO tools by integrating a diverse …
-
New HPO method boosts DSNN accuracy and sustainability
Researchers have developed a multi-objective hyperparameter optimization (HPO) approach for Deep Shift Neural Networks (DSNNs) to promote sustainable deep learning. This method combines multi-fidelity HPO with multi-obj…
-
New strategy boosts noisy evolution algorithms with depth over fidelity
Researchers have developed a new method called Probabilistic Elite Membership (PEM) to improve noisy evolution strategies under fixed evaluation budgets. This approach prioritizes exploring more distribution updates (de…