Related papers: Functional Risk Minimization

Functional Risk Minimization

URL: http://arxiv.org/abs/2412.21149v1
Date: Mon, 30 Dec 2024 18:29:48 GMT
Title: Functional Risk Minimization
Authors: Ferran Alet, Clement Gehring, Tomás Lozano-Pérez, Kenji Kawaguchi, Joshua B. Tenenbaum, Leslie Pack Kaelbling,
Abstract summary: We propose Functional Risk Minimization, a framework where losses compare functions rather than outputs. This results in better performance in supervised, unsupervised, and RL experiments.
Score: 89.85247272720467
License:
Abstract: The field of Machine Learning has changed significantly since the 1970s. However, its most basic principle, Empirical Risk Minimization (ERM), remains unchanged. We propose Functional Risk Minimization~(FRM), a general framework where losses compare functions rather than outputs. This results in better performance in supervised, unsupervised, and RL experiments. In the FRM paradigm, for each data point $(x_i,y_i)$ there is function $f_{\theta_i}$ that fits it: $y_i = f_{\theta_i}(x_i)$. This allows FRM to subsume ERM for many common loss functions and to capture more realistic noise processes. We also show that FRM provides an avenue towards understanding generalization in the modern over-parameterized regime, as its objective can be framed as finding the simplest model that fits the training data.

Related papers

Free Process Rewards without Process Labels [55.14044050782222]
We show that an textitimplicit PRM can be obtained at no additional cost, by simply training an ORM on the cheaper response-level labels. We show that our implicit PRM, when instantiated with the cross-entropy (CE) loss, is more data-efficient and can keep improving generation models even when trained with only one response per instruction.
arXiv Detail & Related papers (2024-12-02T21:20:02Z)
Invariant Risk Minimization Is A Total Variation Model [3.000494957386027]
Invariant risk minimization (IRM) is an arising approach to generalize invariant features to different environments in machine learning. We show that IRM is essentially a total variation based on $L2$ (TV-$ell$) of the learning risk. We propose a novel IRM framework based on the TV-$ell$ model.
arXiv Detail & Related papers (2024-05-02T15:34:14Z)
On the Performance of Empirical Risk Minimization with Smoothed Data [59.3428024282545]
Empirical Risk Minimization (ERM) is able to achieve sublinear error whenever a class is learnable with iid data. We show that ERM is able to achieve sublinear error whenever a class is learnable with iid data.
arXiv Detail & Related papers (2024-02-22T21:55:41Z)
Inverse Reinforcement Learning with Unknown Reward Model based on Structural Risk Minimization [9.44879308639364]
Inverse reinforcement learning (IRL) usually assumes the model of the reward function is pre-specified and estimates the parameter only. A simplistic model is less likely to contain the real reward function, while a model with high complexity leads to substantial cost and risks overfitting. This paper addresses this trade-off by introducing the structural risk minimization (SRM) method from statistical learning.
arXiv Detail & Related papers (2023-12-27T13:23:17Z)
Provably Efficient CVaR RL in Low-rank MDPs [58.58570425202862]
We study risk-sensitive Reinforcement Learning (RL) We propose a novel Upper Confidence Bound (UCB) bonus-driven algorithm to balance interplay between exploration, exploitation, and representation learning in CVaR RL. We prove that our algorithm achieves a sample complexity of $epsilon$-optimal CVaR, where $H$ is the length of each episode, $A$ is the capacity of action space, and $d$ is the dimension of representations.
arXiv Detail & Related papers (2023-11-20T17:44:40Z)
Frustratingly Easy Model Generalization by Dummy Risk Minimization [38.67678021055096]
Dummy Risk Minimization (DuRM) is a frustratingly easy and general technique to improve the generalization of Empirical risk minimization (ERM) We show that DuRM could consistently improve the performance under all tasks with an almost free lunch manner.
arXiv Detail & Related papers (2023-08-04T12:43:54Z)
Federated Empirical Risk Minimization via Second-Order Method [18.548661105227488]
We present an interior point method (IPM) to solve a general empirical risk minimization problem under the federated learning setting. We show that the communication complexity of each iteration of our IPM is $tildeO(d3/2)$, where $d$ is the dimension (i.e., number of features) of the dataset.
arXiv Detail & Related papers (2023-05-27T14:23:14Z)
Robust Empirical Risk Minimization with Tolerance [24.434720137937756]
We study the fundamental paradigm of (robust) $textitempirical risk minimization$ (RERM) We show that a natural tolerant variant of RERM is indeed sufficient for $gamma$-tolerant robust learning VC classes over $mathbbRd$.
arXiv Detail & Related papers (2022-10-02T21:26:15Z)
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments [55.24895403089543]
Domain generalization aims at performing well on unseen test environments with data from a limited number of training environments. We present a new algorithm based on performing iterative feature matching that is guaranteed with high probability to yield a predictor that generalizes after seeing only $O(logd_s)$ environments.
arXiv Detail & Related papers (2021-06-18T04:39:19Z)
On the Minimal Error of Empirical Risk Minimization [90.09093901700754]
We study the minimal error of the Empirical Risk Minimization (ERM) procedure in the task of regression. Our sharp lower bounds shed light on the possibility (or impossibility) of adapting to simplicity of the model generating the data.
arXiv Detail & Related papers (2021-02-24T04:47:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.