TRPO adapts trust region methods for faster RL convergence.
problem Improving RL convergence rates in regularized MDPs.
method Adaptive scaling in TRPO for faster convergence rates.
result First RL result showing faster rates with regularization.
TRSVR combines SVRG with trust-region for faster optimization.
problem Unconstrained nonconvex optimization problems.
method Adaptive stochastic trust-region method with variance reduction.
result Converges to first-order stationary points with SVRG.
Proposes a new algorithm for solving optimization problems with stochastic objectives and equality constraints.
problem Optimization problems with stochastic objectives and deterministic equality constraints.
method Trust-region stochastic sequential quadratic programming (TR-StoSQP) with adaptive relaxation techniques.
result Established a global almost sure convergence guarantee for TR-StoSQP.
Adaptive replication improves stochastic function optimization.
problem Challenges in accurately estimating functions with high variance.
method Trust-region-based Bayesian optimization with adaptive replication.
result Adaptive replication substantially improves solution accuracy and efficiency.
New sampling strategy improves TR algorithms for stochastic optimization.
problem Derivative-free stochastic optimization with Monte Carlo estimates.
method Stratified adaptive sampling to optimize MC sample size.
result Reduced sample complexity and superior efficiency confirmed.
Adaptive norms improve neural network optimization with second-order methods.
problem Optimizing neural networks with second-order methods.
method Regularized Newton methods with adaptive norms, interpreting adaptive gradient methods as trust region methods.
result Ellipsoidal constraints outperform spherical constraints in terms of backpropagations and asymptotic loss value.
New algorithm improves deep learning stability with limited data.
problem Stability and robustness in reinforcement learning with scarce data.
method Uncertainty-aware trust region approach to policy optimization.
result Stable policy updates adapt to uncertainty levels during learning.
TRGPPO improves PPO's exploration, leading to better performance.
problem PPO's exploration is insufficient, especially with bad initialization.
method TRGPPO uses a trust region to adaptively adjust the clipping range.
result TRGPPO achieves better performance bounds and improved exploration.
Improves on-policy RL by reusing data from multiple policies.
problem Lack of reuse of data from previous policies in on-policy RL.
method Adapts replay buffer concept to combine on- and off-policy learning.
result Method outperforms state-of-the-art on-policy RL algorithms.
Two multifidelity trust-region methods use low-fidelity models for efficient optimization.
problem Efficiently solving complex optimization problems with limited data.
method Sketched Trust-Region (STR) and SVD Trust-Region (SVDTR) methods using low-fidelity models.
result Potential gain in efficiency demonstrated through numerical examples.
TRM improves long-horizon LLM RL by masking divergent sequences.
problem Long-horizon reinforcement learning with LLMs suffers from off-policy mismatch and approximation errors.
method Derives and applies trust region bounds to control divergence, proposing Trust Region Masking.
result First non-vacuous monotonic improvement guarantees for long-horizon LLM-RL.
TRM improves long-horizon reinforcement learning for LLMs by masking divergent sequences.
problem Long-horizon reinforcement learning for LLMs suffers from off-policy mismatch and approximation errors.
method Derives and applies trust region bounds to control divergence, proposing Trust Region Masking.
result First non-vacuous monotonic improvement guarantees for long-horizon LLM-RL.
New method solves optimization problems with stochastic objectives and constraints.
problem Optimization problems with stochastic objectives and deterministic constraints.
method Trust-region interior-point stochastic sequential quadratic programming (TR-IP-SSQP) method.
result Global almost-sure convergence to first-order stationary points under standard assumptions.
Trust-region method improves Gaussian mixture models for complex distributions.
problem Learning accurate approximations of complex, multimodal distributions.
method Information-geometric trust regions for principled exploration, lower bound optimization, online component adaptation.
result Improved GMM approximations with better quality and efficiency.
New method solves stochastic optimization problems with random models.
problem Optimizing stochastic objectives with deterministic constraints.
method Trust-Region Sequential Quadratic Programming with random model.
result Global convergence guarantees for first- and second-order stationary points.
Normalizing flows policy improves trust region policy optimization.
problem Improving exploration and avoiding local optima in policy optimization.
method Constructing trust region with KL divergence constraints and using normalizing flows policy.
result Normalizing flows policy significantly improves policy optimization, especially on high-dimensional tasks.
New distributed algorithm for second-order optimization with reduced Hessian computation.
problem Efficiently using second-order methods in distributed optimization with limited communication.
method Distributed training of generalized linear models with adaptive trust-region approach.
result Achieves state-of-the-art results on multiple large datasets.
Proposes a Quasi-Newton trust region method for policy optimization in reinforcement learning.
problem Lack of stepsize selection criterion and slow convergence in gradient descent for policy optimization.
method Uses a trust region method with Quasi-Newton approximation for the Hessian.
result Demonstrates improved performance and efficiency in continuous control tasks.
Unified perspective on natural gradient methods for GMMs, improving variational inference.
problem Efficiently learning multi-modal approximations of complex distributions.
method Comparison and optimization of VIPS and iBayes-GMM methods for Gaussian mixture models.
result Hybrid approach significantly outperforms both VIPS and iBayes-GMM.
Two new algorithms solve nonconvex-strongly concave problems efficiently.
problem Solving nonconvex-strongly concave minimax problems.
method Proposed MINIMAX-TR and MINIMAX-TRACE algorithms.
result Find ( ε , ε ) (ε, \sqrtε) ( ε , ε ) -second order stationary points within O ( ε − 1.5 ) \mathcal{O}(ε^{-1.5}) O ( ε − 1.5 ) iterations. AdaScale-TuRBO improves high-dimensional Bayesian optimization by dynamically scaling the GP lengthscale.
problem Inappropriate lengthscale design in TuRBO's local GP model causes suboptimal performance in high dimensions.
method Proposes AdaScale-TuRBO, which scales the GP lengthscale with both problem dimension and trust region size.
result AdaScale-TuRBO robustly outperforms standard TuRBO and other methods on synthetic and real-world tasks.
A new method improves SVI for high-dimensional, poorly-conditioned distributions.
problem Challenges in existing SVI methods for high-dimensional, poorly-conditioned distributions.
method Trust-region optimization approach leveraging conditional independences and second-order information.
result Superior numerical performance and better scalability in high-dimensional distributions.
TROLL improves RL for LLMs by replacing clipping with a trust region projection.
problem Clipping in RL for LLMs causes instability and suboptimal performance.
method TROLL uses a discrete differentiable trust region projection to replace clipping, balancing computational cost and effectiveness.
result TROLL consistently outperforms PPO-like clipping in training speed, stability, and final success rates.
Bayesian optimization tackles constrained high-dimensional problems with penalties and trust regions.
problem Constrained optimization in high-dimensional black-box settings with expensive evaluations and complex feasibility regions.
method Penalty formulation, surrogate model, trust region strategy, Expected Improvement acquisition function.
result The proposed Trust Region method identifies high-quality feasible solutions with fewer evaluations and maintains stable performance.
Simplified trust region method reduces representation change during fine-tuning.
problem Stability and representational collapse in fine-tuning pre-trained models.
method Replaces adversarial objectives with parametric noise in trust region theory.
result Matches or exceeds previous trust region methods in performance and speed.
TREGO improves EGO for global optimization of high-dimensional problems.
problem Efficient Global Optimization struggles with high dimensions and lacks theoretical guarantees.
method TREGO alternates between EGO steps and local steps within a trust region.
result TREGO outperforms EGO and other methods in black-box optimization problems.
LOL-BO improves latent space Bayesian optimization over structured inputs.
problem Optimizing complex functions over high-dimensional, structured search spaces.
method Adapting trust regions from high-dimensional to structured settings, using a DAE to map inputs into a latent space.
result Achieves up to 20x improvement over state-of-the-art methods.
New algorithm finds local minima in non-convex problems efficiently.
problem Finding local minima in non-convex finite-sum minimization problems.
method Stochastic Trust Region (STR) algorithm combining inexact gradient and Hessian estimation.
result STR finds ( ε , ε ) (ε, \sqrtε) ( ε , ε ) -approximate local minimum with improved efficiency. JAXFit speeds up curve fitting on GPUs.
problem Nonlinear least squares curve fitting problems.
method Trust region method on GPU with automatic differentiation.
result Significantly faster than CPU and other GPU libraries.
Trust-region methods and natural gradients are equivalent in certain policy search scenarios.
problem Improving policy search methods in continuous control tasks.
method Introducing compatible policy search (COPOS) that uses natural parameterization and compatible value function approximation to control entropy loss.
result COPOS yields state-of-the-art results in challenging tasks and reduces entropy loss.
Efficient trust region based attacks reduce adversarial perturbation time significantly.
problem Vulnerability of neural networks to adversarial perturbations requiring time-consuming tuning.
method Trust region optimization for efficient adversarial attack computation.
result Significant speed up of up to 37 times for VGG-16 model on a Titan Xp GPU.
Stochastic variational inference allows for fast posterior inference in complex Bayesian models. However, the algorithm is prone to local optima which can make the quality of the posterior approximation sensitive to the choice of hyperparameters and initialization. We address this problem by replacing the natural gradi…
The paper analyzes and improves a deep learning optimization technique using matrix gradient orthogonality.
problem Improving deep learning training through more effective optimization methods.
method Develops a stochastic non-Euclidean trust-region gradient method for deep learning optimization.
result Proves state-of-the-art convergence results for the proposed algorithm in various scenarios.
Proposes STRON method for large-scale machine learning problems.
problem Large-scale machine learning problems.
method Stochastic Trust Region Inexact Newton (STRON) method using CG to solve trust region subproblem with progressive subsampling.
result Empirical results show efficacy of STRON method.
Local PBO methods improve preferential BO in high-dimensional problems.
problem Efficiently optimizing preferential BO in high-dimensional settings.
method Adapting high-dimensional BO techniques to preferential feedback.
result Local PBO methods reduce cumulative regret compared to global baselines.
HTRPO tackles sparse rewards in RL with improved stability and performance.
problem Sparse rewards in reinforcement learning.
method HTRPO extends TRPO with hindsight and QKL for better policy update stability.
result HTRPO consistently outperforms TRPO and HPG in various sparse reward tasks.
New trust-region algorithms improve ML performance with indefinite Hessians.
problem Training machine learning models with indefinite Hessians.
method Quasi-Newton trust-region framework for indefinite Hessians.
result Proposed methods outperform traditional BFGS and Hessian-free methods.
Enhanced PPO improves stability and performance.
problem Performance instability in PPO.
method Introduces Truly PPO with new clipping function and trust region constraint.
result Improves sample efficiency and performance.
Mirror descent method improved RL algorithms.
problem Improving RL algorithms for better performance.
method Mirror descent method applied to RL, solving trust-region problems.
result MDPO outperforms or matches other RL algorithms in continuous control tasks.
FD-Net predicts future dynamics from data using Hessian-Free TRCG method.
problem Discovering hidden partial differential equations from data.
method Finite-difference inspired convolutional neural network with Hessian-Free TRCG method.
result FD-Net predicts future dynamics efficiently using few trainable parameters.
New formulas for geodesics on Stiefel and flag manifolds using trust-region method.
problem Computing geodesics and logarithms on Stiefel and flag manifolds.
method Closed-form geodesic formulas, trust-region solver, Fréchet derivatives.
result Efficient computation of geodesic distance and logarithm map.
Develops ODRPO to improve RL algorithms with better performance and stability.
problem RL algorithms converge to sub-optimal solutions due to limited policy representation.
method Integrates DRO approach to solve trust region constrained optimization problem without parameterizing policies.
result Achieves globally optimal policy update and higher sample efficiency.
Very recently proximal policy optimization (PPO) algorithms have been proposed as first-order optimization methods for effective reinforcement learning. While PPO is inspired by the same learning theory that justifies trust region policy optimization (TRPO), PPO substantially simplifies algorithm design and improves da…
MF-TRPO optimizes MFGs with finite sample guarantees.
problem Computing approximate Nash equilibria in MFGs.
method Extends TRPO to MFGs, providing convergence guarantees.
result Theoretical guarantees on MF-TRPO's convergence.
Improves inference-time alignment for diffusion models without updating weights.
problem Aligning diffusion models without updating weights for high-reward outputs.
method Trust-Region Iterative Twisted Sequential Monte Carlo (TRI-TSMC) for variance reduction and efficiency.
result Improves primary alignment objectives on text generation tasks.
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement lea…
New approach generates optimal disturbances for controller verification.
problem Optimizing disturbances for controller verification with blackbox access.
method Online learning approach that adaptively generates disturbances based on controller inputs.
result New algorithm (MOTR) outperforms existing methods in simulated examples.
Enhances BO in high dimensions with Newton methods.
problem Challenges in scaling BO to high-dimensional spaces.
method Construct multiple local quadratic models using gradients and Hessians from a global GP, and select new sample points by solving bound-constrained quadratic programs.
result Outperforms existing high-dimensional BO techniques on synthetic and real-world applications.