Machine learning models are often personalized by using group attributes that encode personal characteristics (e.g., sex, age group, HIV status). In such settings, individuals expect to receive more accurate predictions in return for disclosing group attributes to the personalized model. We study when we can tell that a personalized model upholds this principle for every group who provides personal data. We introduce a metric called the benefit of personalization (BoP) to measure the smallest gain in accuracy that any group expects to receive from a personalized model. We describe how the BoP can be used to carry out basic routines to audit a personalized model, including: (i) hypothesis tests to check that a personalized model improves performance for every group; (ii) estimation procedures to bound the minimum gain in personalization. We characterize the reliability of these routines in a finite-sample regime and present minimax bounds on both the probability of error for BoP hypothesis tests and the mean-squared error of BoP estimates. Our results show that we can only claim that personalization improves performance for each group who provides data when we explicitly limit the number of group attributes used by a personalized model. In particular, we show that it is impossible to reliably verify that a personalized classifier with k 19 binary group attributes will benefit every group who provides personal data using a dataset of n = 8 109 samples - one for each person in the world.

A.1 SVRG and SCSG Here we provide the pseudocode for SVRG (Algorithm 2) and SCSG (Algorithm 3) seen in Lei et al. [35]. The idea of SVRG (Algorithm 2) is to reuses past full gradient computations (line 3) to reduce the variance of the current stochastic gradient estimate (line 7) before the parameter update (line 8). Note that N = 1 corresponds to a GD step (i.e., v SVRG achieves linear convergence O(1/T) using the semi-stochastic gradient. The key difference is that SCSG (Algorithm 3) considers a sequence of time-varying batch sizes (Bt and bt) and employs geometric sampling to generate the number of parameter update steps Nt in each iteration (line 6), instead of fixing the batch sizes and the number of updates as done in SVRG. Particularly when finding an -approximate solution (Definition 1) for optimizing smooth non-convex objectives, Lei et al. [35] proves that SCSG is never worse than SVRG in convergence rate and significantly outperforms SVRG when the requiredis small.

Although BERT-style encoder models are heavily used in NLP research, many researchers do not pretrain their own BERTs from scratch due to the high cost of training. In the past half-decade since BERT first rose to prominence, many advances have been made with other transformer architectures and training configurations that have yet to be systematically incorporated into BERT. Here, we introduce MosaicBERT, a BERT-style encoder architecture and training recipe that is empirically optimized for fast pretraining. This efficient architecture incorporates FlashAttention, Attention with Linear Biases (ALiBi), Gated Linear Units (GLU), a module to dynamically remove padded tokens, and low precision LayerNorm into the classic transformer encoder block. The training recipe includes a 30% masking ratio for the Masked Language Modeling (MLM) objective, bfloat16 precision, and vocabulary size optimized for GPU throughput, in addition to best-practices from RoBERTa and other encoder models. When pretrained from scratch on the C4 dataset, this base model achieves a downstream average GLUE (dev) score of 79.6 in 1.13 hours on 8 A100 80 GBGPUs at a cost of roughly $20. We plot extensive accuracy vs. pretraining speed Pareto curves and show that MosaicBERT base and large are consistently Pareto optimal when compared to a competitive BERT base and large. This empirical speed up in pretraining enables researchers and engineers to pretrain custom BERT-style models at low cost instead of finetune on existing generic models.

A.1 Frequency ablation study We perform an ablation study on the coarse-to-fine parameter αd and the number of frequency bands L. In Figure 1, we show the surface reconstruction results of the DTUBuddha model under different frequency parameters. Each model is trained for 300K iterations. In the first row we show the results of surface reconstruction quality under different coarse-to-fine parameters αd. It can be seen that when the parameter is too small, the surface reconstruction tends to be oversmoothed. When the parameter is too large, many artifacts will appear in the reconstruction results.

In this section, we prove the Theorem 2.1, which states a problem P and its' orthogonal transformed problem Q(P) = {{Qxi}Ni=1,f}have identical optimal solutions if Qis orthogonal matrix: QQT = QTQ = I. As we mentioned in Section 2.2, reward R is a function of a1:T (solution sequences), ||xi xj||i,j {1,...N} (relative distances) and f (nodes features). And Let R (P)is optimal value of problem P: i.e. Then, the remaining proof is to show Q(P)has an identical solution set with P. Let optimal solution set Π (P) = {πi(P)}Mi=1, where πi(P)indicates optimal solution of P and M is the number of heterogeneous optimal solution. Conversely, For any πi(P) Π (P), they have sample optimal value with Q(P): R(πi(P);P) = R (P) = R (Q(P)) Thus, πi(P) Π (Q(P)).

Deep reinforcement learning (DRL)-based combinatorial optimization (CO) methods (i.e., DRL-NCO) have shown significant merit over the conventional CO solvers as DRL-NCO is capable of learning CO solvers less relying on problem-specific expert domain knowledge (heuristic method) and supervised labeled data (supervised learning method). This paper presents a novel training scheme, Sym-NCO, which is a regularizer-based training scheme that leverages universal symmetricities in various CO problems and solutions. Leveraging symmetricities such as rotational and reflectional invariance can greatly improve the generalization capability of DRL-NCO because it allows the learned solver to exploit the commonly shared symmetricities in the same CO problem class. Our experimental results verify that our Sym-NCO greatly improves the performance of DRL-NCO methods in four CO tasks, including the traveling salesman problem (TSP), capacitated vehicle routing problem (CVRP), prize collecting TSP (PCTSP), and orienteering problem (OP), without utilizing problem-specific expert domain knowledge. Remarkably, SymNCO outperformed not only the existing DRL-NCO methods but also a competitive conventional solver, the iterative local search (ILS), in PCTSP at 240 faster speed.