On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “MGDA”

MGDA Converges under Generalized Smoothness, Provablycs.LG

MGDA converges under generalized smoothness for neural network optimization.

problem Optimizing neural networks with standard smoothness assumptions not holding.

method Revisited and analyzed MGDA and its stochastic version for generalized

\ell

-smooth MOO problems.

result MGDA and its variants converge to Pareto stationary points with guaranteed CA distance.

Multi-objective optimization Generalized smoothness MGDA Stochastic optimization Pareto stationary point

2024-05-29abs ↗pdf ↗

Reconstructing Physics-Informed Machine Learning for Traffic Flow Modeling: a Multi-Gradient Descent and Pareto Learning Approachcs.LG

This paper improves traffic flow modeling by using multi-gradient descent algorithms for physics-informed machine learning.

problem Combining physics-based and data-driven approaches in traffic flow modeling.

method Introducing multi-gradient descent algorithms to explore the Pareto front in a multi-objective setting.

result Multi-gradient descent algorithms significantly outperform scalarization-based methods in complex PIML scenarios.

traffic flow modeling physics-informed machine learning multi-gradient descent Pareto optimization machine learning

2025-05-19abs ↗pdf ↗

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approachcs.LG

Develops a new method to improve performance in multi-objective learning problems.

problem Gradient bias in multi-objective learning leading to degraded performance.

method Stochastic Multi-objective gradient Correction (MoCo) method that guarantees convergence without increasing batch size.

result Demonstrates effectiveness of MoCo method in simulations on multi-task learning.

multi-objective optimization gradient bias stochastic methods convergence multi-task learning

2022-10-23abs ↗pdf ↗

Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithmscs.LG

Proposes new stochastic algorithms for multi-objective optimization.

problem Multi-objective optimization in machine learning problems.

method Direction-oriented multi-objective formulation and Stochastic Direction-oriented Multi-objective Gradient descent (SDMGrad).

result Stochastic algorithms converge to Pareto stationary points with improved complexities.

multi-objective optimization stochastic algorithms multi-task learning reinforcement learning

2023-05-28abs ↗pdf ↗