New toolkit for directed distances improves flexibility of OT problems.
problem Optimal transport problems with constraints.
method Directed distances between quantile functions.
result Flexibility in solving OT problems enhanced.
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.
168,978 papers · 148 categories
Trend · papers per month
48 results for “direct optimization”
Optimizes CNNs by directing gradients along output channels.
problem Improving generalization error in CNNs.
method Output-channel directed re-weighted L2 or Sobolev metrics.
result Improves generalization error by optimizing gradients.
This letter presents a new spectral-clustering-based approach to the subspace clustering problem. Underpinning the proposed method is a convex program for optimal direction search, which for each data point d finds an optimal direction in the span of the data that has minimum projection on the other data points and non…
Variance reduced stochastic optimization over directed graphs with row and column stochastic weightsmath.OC
AB-SAGA optimizes distributed optimization over directed graphs using variance reduction and stochastic weights.
problem Optimizing distributed stochastic optimization over directed graphs with stochastic weights.
method AB-SAGA combines variance reduction and network-level gradient tracking, using both row and column stochastic weights.
result AB-SAGA converges linearly to the global optimal with a constant step-size and achieves a linear speed-up over centralized methods.
Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancycs.LG
The study analyzes optimization trajectories in neural networks to reveal redundancy and redundancy-reducing strategies.
problem Understanding the directional structure and redundancy in neural network optimization.
method Introducing natural notions of complexity for optimization trajectories and analyzing their directional nature.
result Training only scalar batchnorm parameters can match the performance of training the entire network, indicating potential for hybrid optimization schemes.
Yau's Affine Normal Descent optimizes smooth unconstrained problems with geometrically adapted directions.
problem Optimizing smooth unconstrained problems with geometrically adapted directions.
method Yau's Affine Normal Descent (YAND) uses the equi-affine normal of level-set hypersurfaces as search directions.
result YAND converges globally under standard smoothness assumptions and locally quadratically near nondegenerate minimizers.
Direct policy gradients optimize policies in discrete action spaces using sampling.
problem Optimizing policies in discrete action spaces with direct methods.
method Combining direct optimization and A sampling for policy gradient approximation.
result DirPG algorithms can incorporate domain knowledge and have higher probability of sampling informative gradients.
Optimal neural network approximation for Wasserstein gradient direction via convex optimization.
problem Approximating Wasserstein gradient direction with limited data.
method Two-layer networks with squared-ReLU activations, SDP relaxation.
result Optimal approximation of Wasserstein gradient direction in two-layer networks.
A new method optimizes projection directions for sliced Wasserstein distances.
problem Finding informative projecting directions for sliced Wasserstein distances is computationally expensive.
method Amortized projection optimization to predict directions efficiently.
result Proposed amortized models improve generative modeling performance.
ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Modelscs.LG
ConMeZO speeds up zeroth-order optimization for large language models.
problem Slow convergence in high-dimensional parameter spaces of large language models.
method Adaptive directional sampling in a cone centered around a momentum estimate.
result Achieves the same convergence rate as MeZO but up to 2X faster.
New algorithms estimate Hessians using random directions for faster stochastic optimization.
problem Efficiently estimating Hessians for stochastic optimization.
method Generalized Hessian estimators using random directions and noisy function measurements.
result Asymptotically unbiased estimators with lower bias for more measurements.
Optimizes stochastic linear bandits with efficient, asymptotically optimal algorithm.
problem Optimizing stochastic linear bandits with multiple actions.
method Frequentist information-directed sampling (IDS) with a surrogate for information gain.
result Asymptotically optimal and nearly worst-case optimal in finite time.
Improved SSD for faster and more accurate goodness-of-fit tests and model learning.
problem Optimal slicing directions for SSD are computationally expensive and sub-optimal.
method Relaxed optimal slicing requirement, active sub-space construction, spectral decomposition.
result 14-80x speed-up in goodness-of-fit tests compared to gradient-based alternatives.
Gradient-free method solves infinite-dimensional optimization problems.
problem Optimizing functions in infinite-dimensional spaces.
method Uses directional derivatives and a pre-basis for Hilbert space.
result Proves convergence for solving PDEs using PINNs.
Direct and indirect RL methods classified and compared.
problem Classifying RL methods for sequential decision making.
method Direct RL solves optimal policy directly, indirect RL solves Bellman equation.
result Direct and indirect RL methods are equivalent and can be unified.
MOBO-OSD optimizes multi-objective functions using orthogonal search directions.
problem Challenging multi-objective optimization problem.
method Solves multiple constrained optimization problems along orthogonal search directions.
result Consistently outperforms state-of-the-art algorithms.
Improved ridge regression with Frequent Directions for large-scale tasks.
problem Improving performance of ridge regression for large-scale data.
method Combines Frequent Directions with iterative optimization schemes.
result Achieves high accuracy in estimating bias and variance for sketched ridge regression.
Direct optimization of binary latent VAEs achieves competitive results without sampling.
problem Training VAEs with discrete latent variables using standard methods is challenging.
method Applied evolutionary algorithms to directly optimize discrete latent distributions.
result Direct optimization is efficient and competitive in zero-shot learning.
A new method optimizes slicing directions for SW distances to improve high-dimensional probability measure comparison.
problem Challenging identification of informative slicing directions for SW distances.
method Constrained learning approach to optimize slicing directions, using continuous relaxations and gradient-based primal-dual approach.
result Demonstrated efficacy in learning more informative slicing directions on various high-dimensional data.
A new algorithm for decentralized optimization over directed graphs.
problem Decentralized stochastic optimization over directed networks.
method Gradient tracking and S-ADDOPT algorithm with constant and decaying step-sizes.
result S-ADDOPT converges linearly with constant step-size and sublinearly with decaying step-size.
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.
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.
Novel algorithm for decentralized optimization in time-varying networks with delays.
problem Decentralized optimization in networks with communication delays.
method DT-GO algorithm, applicable to general directed graphs, converges to same complexity as centralized SGD.
result Algorithm DT-GO achieves convergence rates for convex and non-convex objectives, similar to centralized SGD.
Unified framework for stability and generalization of Push-Sum in decentralized learning over directed graphs.
problem Understanding stability and generalization of Push-Sum in decentralized learning over directed networks.
method Developed a unified uniform-stability framework for SGP algorithm, incorporating imbalance-aware consistency bounds.
result Established finite-iteration stability and optimization guarantees for convex and non-convex objectives.
Paper develops online statistical inference methods for stochastic optimization using Kiefer-Wolfowitz algorithms.
problem Online statistical inference of model parameters in stochastic optimization problems.
method Kiefer-Wolfowitz algorithm with random search directions, asymptotic distribution analysis.
result Developed valid confidence intervals for online statistical inference.
Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Ratecs.LG
Stochastic Gradient Descent shows directional bias with moderate learning rates, impacting optimization outcomes.
problem Understanding the bias of SGD with moderate learning rates in practical scenarios.
method Analyzing SGD and GD on an overparameterized linear regression problem.
result SGD converges along large eigenvalue directions, GD along small ones, affecting early stopping outcomes.
Active learning framework for optimizing human preferences in reinforcement learning.
problem Selecting most informative feedback for training models of human preferences.
method Proposes an active learning framework to collect preferential feedback online or offline.
result Errors in DPO logit estimates diminish with more feedback.
BOIDS optimizes high-dimensional problems by guiding optimization with one-dimensional lines.
problem Scaling Bayesian Optimization to high-dimensional problems.
method BOIDS uses a sequence of one-dimensional direction lines guided by an adaptive selection technique and incorporates subspace embedding for efficiency.
result BOIDS outperforms state-of-the-art methods on various synthetic and real-world problems.
RNNs trained on head direction task mimic brain's compass and shifter neurons.
problem Modeling brain's head direction system using neural networks.
method Optimized recurrent neural networks trained on angular velocity integration.
result RNNs naturally emerge with compass and shifter neuron-like properties.
New pricing algorithm learns demand curves and optimizes prices in dynamic markets.
problem Dynamic pricing in markets with incomplete demand information and shifting conditions.
method Actor-Critic Information-Directed Pricing (ACIDP) using IDS algorithms and auditing procedures.
result ACIDP outperforms UCB and TS in market environment shifts.
POTD estimates SDR subspace using optimal transport for binary response.
problem Insufficient performance of existing SDR methods for categorical responses.
method Principal optimal transport direction (POTD) using optimal transport coupling.
result POTD exclusively estimates SDR subspace for error-free class labels.
AdaGrad on linear problems converges to SVM direction.
problem Understanding AdaGrad's implicit bias on linear classification.
method Characterizing AdaGrad's convergence direction as a quadratic optimization problem.
result AdaGrad converges to a direction similar to SVM's solution.
Quantum strategy optimizes wealth growth in a double-or-nothing game.
problem Optimizing wealth growth in a quantum double-or-nothing game.
method Numerical determination of the optimal quantum strategy.
result The quantum strategy outperforms the classical Kelly criterion.
New method prevents deep learning models from forgetting past tasks.
problem Catastrophic forgetting in continual learning.
method Direction-constrained optimization (DCO) with autoencoders.
result Model performance is improved without forgetting past tasks.
Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization performance than SGD, especially for training deep neural networks (DNNs). In this wo…
NetOTC compares and aligns directed or undirected networks via random walk transitions.
problem Comparing and aligning networks of different types and sizes.
method NetOTC uses a transport-based approach to find optimal transition couplings of random walks.
result NetOTC quantifies network differences and provides vertex and edge alignments.
We propose a method to compute optimal control paths for autonomous vehicles deployed for the purpose of inferring a velocity field. In addition to being advected by the flow, the vehicles are able to effect a fixed relative speed with arbitrary control over direction. It is this direction that is used as the basis for…
New PG losses improve decision optimization in misspecified models.
problem Improving decision optimization in models that are not perfectly specified.
method Introducing Perturbation Gradient (PG) losses to connect decision loss with directional derivatives and optimizing using gradient techniques.
result PG losses yield best-in-class policies asymptotically, even in misspecified settings.
Algorithm optimizes non-convex functions using dueling comparisons.
problem Optimizing non-convex functions with limited function evaluations.
method COMP-GP-UCB algorithm, leveraging dueling-choice bandits.
result Theoretical guarantee of on simple regret.
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraintscs.LG
This paper introduces -DPO, a generalized approach to Direct Preference Optimization using diverse divergence constraints.
problem Aligning large language models with human preferences while mitigating safety risks.
method Incorporates diverse divergence constraints to simplify the relationship between reward and optimal policy, eliminating the need for estimating the normalizing constant.
result Optimizes LLMs to align with human preferences more efficiently and under a broader set of divergence constraints.
Variational Optimization forms a differentiable upper bound on an objective. We show that approaches such as Natural Evolution Strategies and Gaussian Perturbation, are special cases of Variational Optimization in which the expectations are approximated by Gaussian sampling. These approaches are of particular interest …
This paper provides a block coordinate descent algorithm to solve unconstrained optimization problems. In our algorithm, computation of function values or gradients is not required. Instead, pairwise comparison of function values is used. Our algorithm consists of two steps; one is the direction estimate step and the o…
DLM for BNNs fails to improve over ELBO optimization.
problem Performance of DLM for Bayesian Neural Networks (BNNs).
method Direct Loss Minimization (DLM) compared to ELBO optimization.
result DLM does not significantly improve over ELBO optimization for BNNs.
We propose directed time series regression, a new approach to estimating parameters of time-series models for use in certainty equivalent model predictive control. The approach combines merits of least squares regression and empirical optimization. Through a computational study involving a stochastic version of a well …
Paper tackles imbalanced binary classification by optimizing precision and recall directly.
problem Imbalanced binary classification where standard accuracy is misleading.
method Exact constrained reformulations for precision and recall optimization.
result ERO framework outperforms state-of-the-art methods on multiple datasets.
Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates. In the discrete case, one can perform reparametrization using the Gumbel-Max trick, but the resulting objective relies on an operation and is non-dif…
This paper uses bandit theory and Thompson Sampling to optimize protein sequences.
problem Optimizing protein sequences using machine learning and directed evolution.
method Proposes a Thompson Sampling-guided Directed Evolution (TS-DE) framework.
result TS-DE achieves a nearly optimal Bayesian regret of order .
New approach optimizes decisions based on uncertainty in predictions.
problem Mismatch between prediction accuracy and decision loss in sequential design.
method Directional uncertainty-guided approach to sequential experimental design.
result Directional uncertainty-based design stops earlier and performs better.