Predictive models are often deployed through existing decision policies that stakeholders are reluctant to change unless a risk constraint requires intervention. We study risk-controlled post-processing: given a deterministic baseline policy, choose a new policy that maximizes agreement with the baseline subject to a chance constraint on a user-specified loss. At the population level, we show that the optimal policy has a threshold structure: it follows the baseline except on contexts where switching to the oracle fallback policy yields a large reduction in conditional violation risk. At the finite-sample level, given a fitted fallback policy and score, we develop a post-processing algorithm that uses calibration data to select a threshold. Leveraging tools from algorithmic stability and stochastic processes, we show that under regularity conditions, in the i.i.d. setting, the expected excess risk of the post-processed policy is $O(\log n/n)$. In the special case when an exact-safe fallback policy is available, the algorithm achieves precise expected risk control under exchangeability. In this setting, we also give high-probability near-optimality guarantees on the post-processed policy. Experiments on a COVID-19 radiograph diagnosis task, an LLM routing problem, and a synthetic multiclass decision task show that targeted post-processing can meet or nearly meet risk budgets while preserving substantially more agreement with the baseline than score-blind random mixing.

Paper "Video-Induced Visual Invariances" focuses on applying different pre-text tasks on We will change the name of 3D ResNet in our model to "2D+1D ResNet". They will be added in the final version. We will further clarify it in the caption of Table 1. We will add this experiment in our final version. The reason why we didn't compare with CBT and A VSlowFast in Table 3 and For further fair comparison, we will add the number of parameters of each model in Table 3 and 4. Result about fixing the backbone and fine-tune the FC layers was reported only in Table 5 as CCL(FC).

The foreign exchange rate (Forex) market is the largest and most crucial trading market in the world followed by the credit market. The foreign exchange rate market determines the exchange rate of different currencies of the world. It involves buying, selling, and exchanging currencies at current or determined prices. Image Source As we can see from the above figure, the average daily trading volume of the Forex market is way too higher than other big stock exchanges in the world. Some of the nice quotes on trading are -- "Trading effectively is about assessing probabilities, not certainties". Yvan Byeajee, Paradigm Shift: How to cultivate equanimity in the face of market uncertainty "The stock market is a device for transferring money from the impatient to the patient".

In view of its power in extracting feature representation, contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning (RL), leading to efficient policy learning in various applications. Despite its tremendous empirical successes, the understanding of contrastive learning for RL remains elusive. To narrow such a gap, we study how RL can be empowered by contrastive learning in a class of Markov decision processes (MDPs) and Markov games (MGs) with low-rank transitions. For both models, we propose to extract the correct feature representations of the low-rank model by minimizing a contrastive loss. Moreover, under the online setting, we propose novel upper confidence bound (UCB)-type algorithms that incorporate such a contrastive loss with online RL algorithms for MDPs or MGs. We further theoretically prove that our algorithm recovers the true representations and simultaneously achieves sample efficiency in learning the optimal policy and Nash equilibrium in MDPs and MGs. We also provide empirical studies to demonstrate the efficacy of the UCB-based contrastive learning method for RL. To the best of our knowledge, we provide the first provably efficient online RL algorithm that incorporates contrastive learning for representation learning. Our codes are available at https://github.com/Baichenjia/Contrastive-UCB.

This article was published as a part of the Data Science Blogathon. Social Media platforms are a common way to share interesting and informative images. Food images, especially related to different cuisines and cultures, are a topic that appears to be frequently trending. Social media platforms like Instagram have a large number of images belonging to different categories. We all might have used the search options on google images or Instagram to browse through yummy-looking cake images for ideas.

This post aims to explain the concept of Word2vec and the mathematics behind the concept in an intuitive way while implementing Word2vec embedding using Gensim in Python. The basic idea of Word2vec is that instead of representing words as one-hot encoding (countvectorizer / tfidfvectorizer) in high dimensional space, we represent words in dense low dimensional space in a way that similar words get similar word vectors, so they are mapped to nearby points. Word2vec is not deep neural network, it turns text into a numeric form that deep neural network can process as input. For example, we can use "artificial" to predict "intelligence". However, the prediction itself is not our goal.

Proximal gradient method has been playing an important role to solve many machine learning tasks, especially for the nonsmooth problems. However, in some machine learning problems such as the bandit model and the black-box learning problem, proximal gradient method could fail because the explicit gradients of these problems are difficult or infeasible to obtain. The gradient-free (zeroth-order) method can address these problems because only the objective function values are required in the optimization. Recently, the first zeroth-order proximal stochastic algorithm was proposed to solve the nonconvex nonsmooth problems. However, its convergence rate is $O(\frac{1}{\sqrt{T}})$ for the nonconvex problems, which is significantly slower than the best convergence rate $O(\frac{1}{T})$ of the zeroth-order stochastic algorithm, where $T$ is the iteration number. To fill this gap, in the paper, we propose a class of faster zeroth-order proximal stochastic methods with the variance reduction techniques of SVRG and SAGA, which are denoted as ZO-ProxSVRG and ZO-ProxSAGA, respectively. In theoretical analysis, we address the main challenge that an unbiased estimate of the true gradient does not hold in the zeroth-order case, which was required in previous theoretical analysis of both SVRG and SAGA. Moreover, we prove that both ZO-ProxSVRG and ZO-ProxSAGA algorithms have $O(\frac{1}{T})$ convergence rates. Finally, the experimental results verify that our algorithms have a faster convergence rate than the existing zeroth-order proximal stochastic algorithm.

We consider the fundamental question of learnability of a hypotheses class in the supervised learning setting and in the general learning setting introduced by Vladimir Vapnik. We survey classic results characterizing learnability in term of suitable notions of complexity, as well as more recent results that establish the connection between learnability and stability of a learning algorithm.