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.
Study improves self-normalized bounds for vector-valued processes beyond sub-Gaussianity.
Calculation of the log-normalizer is a major computational obstacle in applications of log-linear models with large output spaces. The problem of fast normalizer computation has therefore attracted significant attention in the theoretical and applied machine learning literature. In this paper, we analyze a recently pro…
New bounds on self-normalized martingales improve online linear regression performance.
BR-SNIS reduces bias in self-normalized IS without increasing variance.
Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization (BN). Inspired by Self- Normalizing Neural Networks, we propose the self-normaliz…
The paper develops a method for self-normalized inference in adaptive experiments.
A new linear contextual bandit algorithm with improved regret bound.
We improve bounds for stochastic processes, especially those with heavy tails.
Self Normalizing Flows improve normalizing flows by reducing computational complexity.
A new method for evaluating and selecting policies in contextual bandits improves confidence intervals and policy quality.
We study the regret minimization problem in the novel setting of generalized kernelized bandits (GKBs), where we optimize an unknown function belonging to a reproducing kernel Hilbert space (RKHS) having access to samples generated by an exponential family (EF) reward model whose mean is a non-linear function $μ(…
Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNNs) are rare. FNNs that perform well are typically shallow and, therefore cannot …
We provide a brief tutorial on the use of concentration inequalities as they apply to system identification of state-space parameters of linear time invariant systems, with a focus on the fully observed setting. We draw upon tools from the theories of large-deviations and self-normalized martingales, and provide both d…
New method improves feature importance assessment in random forests.
Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently incorporate normalization based on central limit theory. SELU is a monotonically incre…
New algorithm reduces reinforcement learning regret for linear MDPs with unknown transitions.
High-risk domains require reliable confidence estimates from predictive models. Deep latent variable models provide these, but suffer from the rigid variational distributions used for tractable inference, which err on the side of overconfidence. We propose Stochastic Quantized Activation Distributions (SQUAD), which im…
Finite-time queue peaks in stochastic networks have logarithmic scaling after geometric thresholds.
This paper develops dimension-agnostic inference methods for high-dimensional data.
Online learning to rank is a core problem in machine learning. In Lattimore et al. (2018), a novel online learning algorithm was proposed based on topological sorting. In the paper they provided a set of self-normalized inequalities (a) in the algorithm as a criterion in iterations and (b) to provide an upper bound for…
New framework for evaluating ad auctions using stochastic modeling.
The paper proposes a method for constructing confidence sets that adapt to the cardinality of the smallest component of a mean vector.
A tutorial on non-asymptotic system identification methods.
This paper studies semiparametric contextual bandits, a generalization of the linear stochastic bandit problem where the reward for an action is modeled as a linear function of known action features confounded by an non-linear action-independent term. We design new algorithms that achieve regret …
A new aggregation strategy improves GNN performance and learning dynamics.
The study reveals the efficiency of sampling from tilted distributions.
Cost-aware SBI reduces expensive simulations in complex models.
New inequalities for matrix supermartingales converge under various conditions.
We develop a probabilistic framework for sequential random projection.
This work considers the problem of modified portmanteau tests for testing the adequacy of FARIMA models under the assumption that the errors are uncorrelated but not necessarily independent (i.e. weak FARIMA). We first study the joint distribution of the least squares estimator and the noise empirical autocovariances. …
Quantile regression is an increasingly important empirical tool in economics and other sciences for analyzing the impact of a set of regressors on the conditional distribution of an outcome. Extremal quantile regression, or quantile regression applied to the tails, is of interest in many economic and financial applicat…
In this paper, we analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics. An unknown discrete-time linear system evolves over time under Gaussian noise without external inputs. The objective is to recover the system parameters as well as the Kalm…
Off-policy evaluation (OPE) in both contextual bandits and reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. The problem's importance has attracted many proposed solutions, including importance sampling (IS), self…
Learning the minimum/maximum mean among a finite set of distributions is a fundamental sub-task in planning, game tree search and reinforcement learning. We formalize this learning task as the problem of sequentially testing how the minimum mean among a finite set of distributions compares to a given threshold. We deve…
Bayesian optimization tackles uncertainty in context variables.
New neural network approach mitigates vanishing/exploding gradients.
The generalized linear bandit framework has attracted a lot of attention in recent years by extending the well-understood linear setting and allowing to model richer reward structures. It notably covers the logistic model, widely used when rewards are binary. For logistic bandits, the frequentist regret guarantees of e…
Paper proposes a federated learning method for quantile inference with local differential privacy.
Wavelet-based online learning adapts to noisy Besov spaces with high probability.
Energy-based models (EBMs) are powerful probabilistic models, but suffer from intractable sampling and density evaluation due to the partition function. As a result, inference in EBMs relies on approximate sampling algorithms, leading to a mismatch between the model and inference. Motivated by this, we consider the sam…
Improved sampling efficiency for inverse problems using variance-reduced diffusion methods.
New algorithm reduces best-in-class regret in contextual bandits.
Current approaches to amortizing Bayesian inference focus solely on approximating the posterior distribution. Typically, this approximation is, in turn, used to calculate expectations for one or more target functions - a computational pipeline which is inefficient when the target function(s) are known upfront. In this …
In high dimensional settings where a small number of regressors are expected to be important, the Lasso estimator can be used to obtain a sparse solution vector with the expectation that most of the non-zero coefficients are associated with true signals. While several approaches have been developed to control the inclu…
New algorithms reduce regret in neural logistic bandits.
New summary measures reveal geometric structure in weighted measures on manifolds.
New auto-encoder handles varying noise levels without retraining.
This paper achieves first-order regret bounds in reinforcement learning with large state spaces.