MINIMIZATION
SHARPNESS-AWARE MINIMIZATION FOR EFFICIENTLY IMPROVING GENERALIZATION论文阅读笔记
Intro 在训练集上最小化损失很可能导致泛化性低，因为当今模型的过参数化会导致training loss的landscape异常复杂且非凸，包含很多local/global minima，因此优化器的选择至关重要。loss landscape的几何性质（特别是minima的flatness）与泛化 ......
【位运算】ABC281F Xor Minimization 题解
ABC281F 先将每一个 \(a_i\) 二进制拆分。 因为每一位的 \(\text{xor}\) 运算是互不影响的，于是可以考虑每一位。 从高位到低位考虑，因为 \(a_i < 2^{30}\)，所以二进制状态下的 \(a_i\) 的长度是 \(\le 29\) 的。 假设在考虑 \(bit\) ......
Graph transduction via alternating minimization
目录概符号说明GTAM交替优化求解 Wang J., Jebara T. and Chang S. Graph transduction via alternating minimization. ICML, 2008. 概 一种对类别不均更鲁棒的半监督算法. 符号说明 \(\mathcal{X}_ ......
论文解读（MTEM）《Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification》
Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classific ......
题解 Yet Another Minimization Problem
[Yet Another Minimization Problem](https://www.luogu.com.cn/problem/CF868F) 神仙题。 第一眼看上去就是 DP。 定义 $f_{i,j}$ 表示当前点 $i$，分 $j$ 段的最小费用。 $f_{i,j}= \min(f_{i ......
Regret Minimization Experience Replay in Off-Policy Reinforcement Learning
**发表时间：**2021 (NeurIPS 2021) **文章要点：**理论表明，更高的hindsight TD error，更加on policy,以及更准的target Q value的样本应该有更高的采样权重（The theory suggests that data with highe ......
AtCoder Regular Contest 153 E Deque Minimization
[洛谷传送门](https://www.luogu.com.cn/problem/AT_arc153_e "洛谷传送门") [AtCoder 传送门](https://atcoder.jp/contests/arc153/tasks/arc153_e "AtCoder 传送门") 我们考虑给定 $X ......
Yet Another Minimization Problem（CF1637D）
## $\text{Des}$ You are given two arrays $ a $ and $ b $ , both of length $ n $ . You can perform the following operation any number of times (possibl ......
AtCoder Regular Contest 130 C Digit Sum Minimization
[洛谷传送门](https://www.luogu.com.cn/problem/AT_arc130_c "洛谷传送门") [AtCoder 传送门](https://atcoder.jp/contests/arc130/tasks/arc130_c "AtCoder 传送门") 分类讨论，但是写起 ......
迁移学习《mixup: Beyond Empirical Risk Minimization》
论文信息 论文标题：mixup: Beyond Empirical Risk Minimization论文作者：Takeru Miyato, S. Maeda, Masanori Koyama, S. Ishii论文来源：2018 ICLR论文地址：download 论文代码：download视屏讲 ......