arXiv research

The paper proves a regret bound for a sub-Gaussian mixture on unbounded data.

Paper introduces a new gradient estimator for SNNs.

New method detects and clusters market regimes in multidimensional data.

We develop asymptotically optimal policies for the multi armed bandit (MAB), problem, under a cost constraint. This model is applicable in situations where each sample (or activation) from a population (bandit) incurs a known bandit dependent cost. Successive samples from each population are iid random variables with u…

PWSHAP provides targeted explanations for complex models.

New method approximates diffusion process posteriors using moment functions.

URGE improves diffusion model quality without gradients or Hessian.

A new method for stochastic optimal control improves accuracy over existing techniques.

We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect the output of the network, and suggest Path-SGD, which is an approximate steepest descent method with …

We study the detailed path-wise behavior of the discrete-time Langevin algorithm for non-convex Empirical Risk Minimization (ERM) through the lens of metastability, adopting some techniques from Berglund and Gentz (2003. For a particular local optimum of the empirical risk, with an arbitrary initialization, we show tha…

GANs can approximate SDEs for large time steps.

Paper develops SINNOs for approximating stochastic processes.

EnKF's update is shown to be similar to Matheron's method in Gaussian process regression.

New method transforms complex stochastic equations into simpler ones for efficient simulation.

Paper presents a new insurance model equation for diverse structures.

AdaPID optimizes diffusion-based samplers by dynamically adjusting schedules.

We consider the portfolio choice problem for a long-run investor in a general continuous semimartingale model. We suggest to use path-wise growth optimality as the decision criterion and encode preferences through restrictions on the class of admissible wealth processes. Specifically, the investor is only interested in…

Study on Langevin dynamics for recovering planted signals in spiked matrix models.

New methods for calculating credit valuation adjustment with reduced noise and faster computation.

New algorithm for continuous-time switching systems using variational inference.

We introduce a new deep convolutional neural network, CrescendoNet, by stacking simple building blocks without residual connections. Each Crescendo block contains independent convolution paths with increased depths. The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks. In exp…

RL helps optimize TVS fund composition for volatility control.

Regret minimization is treated as the golden rule in the traditional study of online learning. However, regret minimization algorithms tend to converge to the static optimum, thus being suboptimal for changing environments. To address this limitation, new performance measures, including dynamic regret and adaptive regr…

The paper analyzes the sliding regret of stochastic bandit algorithms.

This paper analyzes regret bounds for Gaussian process Thompson sampling.

The notion of \emph{policy regret} in online learning is a well defined? performance measure for the common scenario of adaptive adversaries, which more traditional quantities such as external regret do not take into account. We revisit the notion of policy regret and first show that there are online learning settings …

Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to a…

In this paper, we present a method for the accurate estimation of the derivative (aka.~sensitivity) of expectations of functions involving an indicator function by combining a stochastic algorithmic differentiation and a regression. The method is an improvement of the approach presented in [Risk Magazine April 2018]. T…

Balances the regret of different algorithms in bandit and RL problems.

Data-driven model selection reduces regret in sequential decisions.

Optimistic Hedge achieves optimal regret bounds in two-player zero-sum games.

We consider an online learning process to forecast a sequence of outcomes for nonconvex models. A typical measure to evaluate online learning algorithms is regret but such standard definition of regret is intractable for nonconvex models even in offline settings. Hence, gradient based definition of regrets are common f…

Optimal switching regret for all segmentations in online convex optimisation.

New approach for distributed online optimization of non-convex losses with sublinear regret.

Regret minimization is a powerful tool for solving large-scale problems; it was recently used in breakthrough results for large-scale extensive-form game solving. This was achieved by composing simplex regret minimizers into an overall regret-minimization framework for extensive-form game strategy spaces. In this paper…

New algorithm SELECT minimizes satisficing regret in bandits.

We study the Thompson sampling algorithm in an adversarial setting, specifically, for adversarial bit prediction. We characterize the bit sequences with the smallest and largest expected regret. Among sequences of length $T$ with $k < \frac{T}{2}$ zeros, the sequences of largest regret consist of alternating zeros and …

This paper considers the stability of online learning algorithms and its implications for learnability (bounded regret). We introduce a novel quantity called {\em forward regret} that intuitively measures how good an online learning algorithm is if it is allowed a one-step look-ahead into the future. We show that given…

Paper introduces a new $G^\star$ regret measure for online convex optimization with smooth losses.

Bandit algorithms struggle with consistent performance and robustness.

Paper improves worst-case regret bounds for RLSVI in reinforcement learning.

Paper solves no-swap regret minimization for combinatorial bandits with polylogarithmic dependence on N.

New algorithms reduce dynamic regret in non-stationary RL environments.

New algorithms minimize simple and cumulative regret in contextual bandits.

Paper explores rate-preserving reductions between Blackwell approachability and no-regret learning.

Algorithm minimizes regret and converges to equilibria in Markov games.

There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side in…

New algorithm achieves both static and dynamic regret optimally against an oblivious adversary for deterministic losses.