arXiv research

Innovative game theory approach optimizes survival analysis metrics.

New algorithms handle online prediction with bandit and delayed feedback, improving regret bounds.

Proposes stabilized weights for causal inference using isotonic calibration.

Adversarial robustness improved by sparsity in network weights.

The paper proves geometric inequalities in sphere using locally constrained flows.

Efficient algorithm for learning MDPs with unknown transitions and bandit feedback.

New method tightens federated probe-logit distillation rates under varying bandwidths.

This paper proposes a method for solving optimization problems in which the decision-maker cannot evaluate the objective function, but rather can only express a preference such as "this is better than that" between two candidate decision vectors. The algorithm described in this paper aims at reaching the global optimiz…

Kernelized bandit algorithm tackles adaptive contextual bandits with single-index models.

New algorithm reduces unfairness in bandit problems by balancing exploration and exploitation.

Study shows gradient variance increases during deep learning training, contrary to common belief.

Researchers compare different gradient methods for ridge regression, finding conjugate gradients have similar performance.

Gradient descent implicitly regularizes neural networks by penalizing large loss gradients.

Policy gradient aims to maximize expected return using gradient ascent.

Improved sampling method using regularized Stein Variational Gradient Flow.

In this work we revisit gradient regularization for adversarial robustness with some new ingredients. First, we derive new per-image theoretical robustness bounds based on local gradient information. These bounds strongly motivate input gradient regularization. Second, we implement a scaleable version of input gradient…

FGD reduces noisy gradient variance in SGD for neural networks.

Proposes a new adaptive gradient method based on gradient differences.

New methods using natural gradient for structured optimization.

CProp scales learning rate based on past gradient direction.

The present paper develops a novel aggregated gradient approach for distributed machine learning that adaptively compresses the gradient communication. The key idea is to first quantize the computed gradients, and then skip less informative quantized gradient communications by reusing outdated gradients. Quantizing and…

Paper examines the structure of stochastic gradients in deep learning.

Faster policy learning via continuous-time gradients.

Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparameterization gradients, or gradient estimates computed via the "reparameterization trick," represent a class of noisy gradients often used in Monte Carlo variational inference (MCVI). However, when these gradient estimator…

Gradient flossing stabilizes RNN training by controlling Lyapunov exponents.

Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value gradients is desirable as policy improvement occurs along the direction of stee…

Adaptive methods improve gradient descent and proximal gradient for convex optimization.

Stein variational gradient decent (SVGD) has been shown to be a powerful approximate inference algorithm for complex distributions. However, the standard SVGD requires calculating the gradient of the target density and cannot be applied when the gradient is unavailable. In this work, we develop a gradient-free variant …

We present ErasureHead, a new approach for distributed gradient descent (GD) that mitigates system delays by employing approximate gradient coding. Gradient coded distributed GD uses redundancy to exactly recover the gradient at each iteration from a subset of compute nodes. ErasureHead instead uses approximate gradien…

In this note, we observe the behavior of gradient flow and discrete and noisy gradient descent in some simple settings. It is commonly noted that addition of noise to gradient descent can affect the trajectory of gradient descent. Here, we run some computer experiments for gradient descent on some simple functions, and…

SGLRW improves robustness of stochastic gradient MCMC methods.

The reparameterization gradient has become a widely used method to obtain Monte Carlo gradients to optimize the variational objective. However, this technique does not easily apply to commonly used distributions such as beta or gamma without further approximations, and most practical applications of the reparameterizat…

New method for natural policy gradients converges linearly.

Blind Descent avoids gradient issues, using a different learning approach.

This paper bridges variational inference and Wasserstein gradient flows.

Paper proposes new gradient codes for robust distributed machine learning.

A new gradient tree boosting framework reduces variance and accelerates performance.

FSGLD improves federated data sampling by correcting noisy gradients.

Proposes VSGD optimizer combining probabilistic and gradient-based methods.

Adaptive batch sizes improve local gradient methods in distributed training.

Proposes log density gradient to improve reinforcement learning sample complexity.

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient updates should be statistically indistinguishable from each other. We enforce this c…

Interpreting gradient methods as fixed-point iterations, we provide a detailed analysis of those methods for minimizing convex objective functions. Due to their conceptual and algorithmic simplicity, gradient methods are widely used in machine learning for massive data sets (big data). In particular, stochastic gradien…

COMP-AMS optimizes distributed training with compressed gradients, achieving similar accuracy with less communication.

Paper introduces a new multi-kernel algorithm for better gradient approximation.

DBQPG improves policy gradient estimation with fewer samples.

Gradient sparsification enhances privacy-preserving machine learning models.

This paper presents a new class of gradient methods for distributed machine learning that adaptively skip the gradient calculations to learn with reduced communication and computation. Simple rules are designed to detect slowly-varying gradients and, therefore, trigger the reuse of outdated gradients. The resultant gra…